Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 960 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.4683. Min Range: -12.4683
Max Act: 12.4683. Min Act: -0.1700
Data Index: 3947314 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.4683. Min Range: -12.4683
Max Act: 12.1558. Min Act: -0.1700
Data Index: 4886734 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.4683. Min Range: -12.4683
Max Act: 11.9683. Min Act: -0.1700
Data Index: 6639053 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.4683. Min Range: -12.4683
Max Act: 12.0308. Min Act: -0.1700
Data Index: 8813416 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.4683. Min Range: -12.4683
Max Act: 11.9683. Min Act: -0.1700
Data Index: 3802195 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.4683. Min Range: -12.4683
Max Act: 12.0308. Min Act: -0.1700
Data Index: 1112655 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.4683. Min Range: -12.4683
Max Act: 11.9058. Min Act: -0.1700
Data Index: 4138660 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.4683. Min Range: -12.4683
Max Act: 11.9058. Min Act: -0.1700
Data Index: 5666448 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.4683. Min Range: -12.4683
Max Act: 11.8433. Min Act: -0.1700
Data Index: 3044406 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.4683. Min Range: -12.4683
Max Act: 11.9058. Min Act: -0.1700
Data Index: 4582044 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.4683. Min Range: -12.4683
Max Act: 11.7808. Min Act: -0.1700
Data Index: 2969381 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.4683. Min Range: -12.4683
Max Act: 11.8433. Min Act: -0.1700
Data Index: 2757906 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.4683. Min Range: -12.4683
Max Act: 11.7808. Min Act: -0.1700
Data Index: 5386247 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.4683. Min Range: -12.4683
Max Act: 11.7183. Min Act: -0.1700
Data Index: 8721449 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.4683. Min Range: -12.4683
Max Act: 11.7808. Min Act: -0.1700
Data Index: 6467686 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.4683. Min Range: -12.4683
Max Act: 11.7183. Min Act: -0.1700
Data Index: 5530629 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.4683. Min Range: -12.4683
Max Act: 11.6558. Min Act: -0.1700
Data Index: 4884270 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.4683. Min Range: -12.4683
Max Act: 11.5933. Min Act: -0.1700
Data Index: 2474072 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.4683. Min Range: -12.4683
Max Act: 11.6558. Min Act: -0.1700
Data Index: 7476128 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.4683. Min Range: -12.4683
Max Act: 11.6558. Min Act: -0.1700
Data Index: 6154266 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19