Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 964 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4036. Min Range: -5.4036
Max Act: 5.4036. Min Act: -0.1700
Data Index: 4121499 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4036. Min Range: -5.4036
Max Act: 5.3724. Min Act: -0.1700
Data Index: 5573384 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4036. Min Range: -5.4036
Max Act: 5.3411. Min Act: -0.1700
Data Index: 970177 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4036. Min Range: -5.4036
Max Act: 5.3411. Min Act: -0.1700
Data Index: 5108991 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4036. Min Range: -5.4036
Max Act: 5.3411. Min Act: -0.1700
Data Index: 6281732 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4036. Min Range: -5.4036
Max Act: 5.3099. Min Act: -0.1700
Data Index: 2979888 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4036. Min Range: -5.4036
Max Act: 5.3099. Min Act: -0.1700
Data Index: 3656759 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4036. Min Range: -5.4036
Max Act: 5.2786. Min Act: -0.1700
Data Index: 3414339 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4036. Min Range: -5.4036
Max Act: 5.2786. Min Act: -0.1700
Data Index: 7988772 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4036. Min Range: -5.4036
Max Act: 5.2786. Min Act: -0.1700
Data Index: 858333 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4036. Min Range: -5.4036
Max Act: 5.2474. Min Act: -0.1700
Data Index: 4529738 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4036. Min Range: -5.4036
Max Act: 5.2474. Min Act: -0.1700
Data Index: 3189577 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4036. Min Range: -5.4036
Max Act: 5.2474. Min Act: -0.1700
Data Index: 1726761 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4036. Min Range: -5.4036
Max Act: 5.2474. Min Act: -0.1700
Data Index: 6725979 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4036. Min Range: -5.4036
Max Act: 5.2474. Min Act: -0.1700
Data Index: 4611921 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4036. Min Range: -5.4036
Max Act: 5.2474. Min Act: -0.1700
Data Index: 6503012 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4036. Min Range: -5.4036
Max Act: 5.2474. Min Act: -0.1700
Data Index: 5792223 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4036. Min Range: -5.4036
Max Act: 5.2474. Min Act: -0.1700
Data Index: 5055430 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4036. Min Range: -5.4036
Max Act: 5.2474. Min Act: -0.1700
Data Index: 4659663 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4036. Min Range: -5.4036
Max Act: 5.2474. Min Act: -0.1700
Data Index: 4612927 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19