Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1936 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0203. Min Range: -5.0203
Max Act: 5.0203. Min Act: -0.1700
Data Index: 5036397 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0203. Min Range: -5.0203
Max Act: 4.8953. Min Act: -0.1700
Data Index: 6886207 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0203. Min Range: -5.0203
Max Act: 4.8328. Min Act: -0.1700
Data Index: 7259744 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0203. Min Range: -5.0203
Max Act: 4.8328. Min Act: -0.1700
Data Index: 7284672 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0203. Min Range: -5.0203
Max Act: 4.8328. Min Act: -0.1700
Data Index: 12601 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0203. Min Range: -5.0203
Max Act: 4.7391. Min Act: -0.1700
Data Index: 1385350 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0203. Min Range: -5.0203
Max Act: 4.7703. Min Act: -0.1700
Data Index: 3315639 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0203. Min Range: -5.0203
Max Act: 4.7391. Min Act: -0.1700
Data Index: 4113755 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0203. Min Range: -5.0203
Max Act: 4.7078. Min Act: -0.1700
Data Index: 1276963 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0203. Min Range: -5.0203
Max Act: 4.7078. Min Act: -0.1700
Data Index: 4065465 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0203. Min Range: -5.0203
Max Act: 4.7078. Min Act: -0.1700
Data Index: 7254029 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0203. Min Range: -5.0203
Max Act: 4.6766. Min Act: -0.1700
Data Index: 2381518 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0203. Min Range: -5.0203
Max Act: 4.6766. Min Act: -0.1700
Data Index: 4575605 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0203. Min Range: -5.0203
Max Act: 4.6141. Min Act: -0.1700
Data Index: 424995 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0203. Min Range: -5.0203
Max Act: 4.6141. Min Act: -0.1700
Data Index: 2539415 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0203. Min Range: -5.0203
Max Act: 4.6141. Min Act: -0.1700
Data Index: 7593771 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0203. Min Range: -5.0203
Max Act: 4.5828. Min Act: -0.1700
Data Index: 1073420 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0203. Min Range: -5.0203
Max Act: 4.5828. Min Act: -0.1700
Data Index: 6490638 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0203. Min Range: -5.0203
Max Act: 4.5828. Min Act: -0.1700
Data Index: 6929724 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0203. Min Range: -5.0203
Max Act: 4.5516. Min Act: -0.1700
Data Index: 2405928 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19