Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3164 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.6103. Min Act: -0.1700
Data Index: 7229099 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.5478. Min Act: -0.1700
Data Index: 5146438 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.4853. Min Act: -0.1700
Data Index: 6410522 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.4540. Min Act: -0.1700
Data Index: 2187418 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.4228. Min Act: -0.1700
Data Index: 6587904 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.4228. Min Act: -0.1700
Data Index: 1136381 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.3603. Min Act: -0.1700
Data Index: 6399404 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.3603. Min Act: -0.1700
Data Index: 6645070 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.3290. Min Act: -0.1700
Data Index: 2657650 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.3290. Min Act: -0.1700
Data Index: 5702389 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.3290. Min Act: -0.1700
Data Index: 4347043 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.3603. Min Act: -0.1700
Data Index: 7206939 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.3290. Min Act: -0.1700
Data Index: 3983126 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.2978. Min Act: -0.1700
Data Index: 2429665 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.2978. Min Act: -0.1700
Data Index: 2745876 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.2665. Min Act: -0.1700
Data Index: 4543494 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.2665. Min Act: -0.1700
Data Index: 8301117 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.2665. Min Act: -0.1700
Data Index: 3070660 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.2665. Min Act: -0.1700
Data Index: 43871 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.2040. Min Act: -0.1700
Data Index: 4732966 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19