Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2444 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9138. Min Range: -8.9138
Max Act: 8.9138. Min Act: -0.1700
Data Index: 2023863 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9138. Min Range: -8.9138
Max Act: 8.7888. Min Act: -0.1700
Data Index: 369039 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9138. Min Range: -8.9138
Max Act: 8.7263. Min Act: -0.1700
Data Index: 5260350 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9138. Min Range: -8.9138
Max Act: 8.7263. Min Act: -0.1700
Data Index: 3783515 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9138. Min Range: -8.9138
Max Act: 8.6638. Min Act: -0.1700
Data Index: 4720905 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9138. Min Range: -8.9138
Max Act: 8.5388. Min Act: -0.1700
Data Index: 1318963 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9138. Min Range: -8.9138
Max Act: 8.4138. Min Act: -0.1700
Data Index: 4550751 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9138. Min Range: -8.9138
Max Act: 8.4763. Min Act: -0.1700
Data Index: 1058781 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9138. Min Range: -8.9138
Max Act: 8.4138. Min Act: -0.1700
Data Index: 5906886 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9138. Min Range: -8.9138
Max Act: 8.3513. Min Act: -0.1700
Data Index: 3798362 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9138. Min Range: -8.9138
Max Act: 8.2888. Min Act: -0.1700
Data Index: 1377950 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9138. Min Range: -8.9138
Max Act: 8.2263. Min Act: -0.1700
Data Index: 6185600 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9138. Min Range: -8.9138
Max Act: 8.1638. Min Act: -0.1700
Data Index: 2289148 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9138. Min Range: -8.9138
Max Act: 8.2263. Min Act: -0.1700
Data Index: 5764942 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9138. Min Range: -8.9138
Max Act: 8.2263. Min Act: -0.1700
Data Index: 4668157 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9138. Min Range: -8.9138
Max Act: 8.2263. Min Act: -0.1700
Data Index: 6862611 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9138. Min Range: -8.9138
Max Act: 8.2263. Min Act: -0.1700
Data Index: 3830846 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9138. Min Range: -8.9138
Max Act: 8.2263. Min Act: -0.1700
Data Index: 413046 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9138. Min Range: -8.9138
Max Act: 8.2263. Min Act: -0.1700
Data Index: 3302199 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9138. Min Range: -8.9138
Max Act: 8.2263. Min Act: -0.1700
Data Index: 590041 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19