Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1057 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.6715. Min Act: -0.1700
Data Index: 4426536 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.6715. Min Act: -0.1700
Data Index: 6062100 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.6402. Min Act: -0.1700
Data Index: 5196602 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.6090. Min Act: -0.1700
Data Index: 1487668 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.5777. Min Act: -0.1700
Data Index: 4253607 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.5777. Min Act: -0.1700
Data Index: 8758652 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.5777. Min Act: -0.1700
Data Index: 2994909 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.5465. Min Act: -0.1700
Data Index: 1208490 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.5777. Min Act: -0.1700
Data Index: 3147356 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.5152. Min Act: -0.1700
Data Index: 1117341 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.5465. Min Act: -0.1700
Data Index: 5147475 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.5465. Min Act: -0.1700
Data Index: 3877939 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.5465. Min Act: -0.1700
Data Index: 3849343 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.5152. Min Act: -0.1700
Data Index: 6257668 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.5465. Min Act: -0.1700
Data Index: 812719 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.5465. Min Act: -0.1700
Data Index: 6493089 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.5152. Min Act: -0.1700
Data Index: 7571383 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.5152. Min Act: -0.1700
Data Index: 7200292 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.4840. Min Act: -0.1700
Data Index: 6265416 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.4527. Min Act: -0.1700
Data Index: 85887 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19