Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4101 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7135. Min Range: -6.7135
Max Act: 6.7135. Min Act: -0.1700
Data Index: 63071 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7135. Min Range: -6.7135
Max Act: 6.6823. Min Act: -0.1700
Data Index: 238620 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7135. Min Range: -6.7135
Max Act: 6.3698. Min Act: -0.1700
Data Index: 3009770 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7135. Min Range: -6.7135
Max Act: 6.3385. Min Act: -0.1700
Data Index: 547223 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7135. Min Range: -6.7135
Max Act: 6.3073. Min Act: -0.1700
Data Index: 3499835 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7135. Min Range: -6.7135
Max Act: 6.3385. Min Act: -0.1700
Data Index: 20964 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7135. Min Range: -6.7135
Max Act: 6.3073. Min Act: -0.1700
Data Index: 1135001 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7135. Min Range: -6.7135
Max Act: 6.2760. Min Act: -0.1700
Data Index: 4022796 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7135. Min Range: -6.7135
Max Act: 6.2135. Min Act: -0.1700
Data Index: 1306643 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7135. Min Range: -6.7135
Max Act: 6.2448. Min Act: -0.1700
Data Index: 2052853 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7135. Min Range: -6.7135
Max Act: 6.2448. Min Act: -0.1700
Data Index: 3516943 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7135. Min Range: -6.7135
Max Act: 6.2448. Min Act: -0.1700
Data Index: 2852751 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7135. Min Range: -6.7135
Max Act: 6.2135. Min Act: -0.1700
Data Index: 6893768 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7135. Min Range: -6.7135
Max Act: 6.2135. Min Act: -0.1700
Data Index: 4044097 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7135. Min Range: -6.7135
Max Act: 6.2135. Min Act: -0.1700
Data Index: 2197325 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7135. Min Range: -6.7135
Max Act: 6.2135. Min Act: -0.1700
Data Index: 8430874 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7135. Min Range: -6.7135
Max Act: 6.2135. Min Act: -0.1700
Data Index: 2080857 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7135. Min Range: -6.7135
Max Act: 6.1823. Min Act: -0.1700
Data Index: 5853261 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7135. Min Range: -6.7135
Max Act: 6.1510. Min Act: -0.1700
Data Index: 2547365 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7135. Min Range: -6.7135
Max Act: 6.1823. Min Act: -0.1700
Data Index: 3851398 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19