Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5847 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9551. Min Range: -5.9551
Max Act: 5.9551. Min Act: -0.1700
Data Index: 4782147 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9551. Min Range: -5.9551
Max Act: 5.7988. Min Act: -0.1700
Data Index: 2903083 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9551. Min Range: -5.9551
Max Act: 5.7051. Min Act: -0.1700
Data Index: 8025949 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9551. Min Range: -5.9551
Max Act: 5.6426. Min Act: -0.1700
Data Index: 702583 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9551. Min Range: -5.9551
Max Act: 5.5801. Min Act: -0.1700
Data Index: 6448369 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9551. Min Range: -5.9551
Max Act: 5.5801. Min Act: -0.1700
Data Index: 4279809 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9551. Min Range: -5.9551
Max Act: 5.5488. Min Act: -0.1700
Data Index: 6695024 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9551. Min Range: -5.9551
Max Act: 5.5488. Min Act: -0.1700
Data Index: 3722108 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9551. Min Range: -5.9551
Max Act: 5.5488. Min Act: -0.1700
Data Index: 2597904 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9551. Min Range: -5.9551
Max Act: 5.4863. Min Act: -0.1700
Data Index: 4997239 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9551. Min Range: -5.9551
Max Act: 5.5176. Min Act: -0.1700
Data Index: 8040228 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9551. Min Range: -5.9551
Max Act: 5.5176. Min Act: -0.1700
Data Index: 6115515 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9551. Min Range: -5.9551
Max Act: 5.4863. Min Act: -0.1700
Data Index: 67400 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9551. Min Range: -5.9551
Max Act: 5.4551. Min Act: -0.1700
Data Index: 3404977 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9551. Min Range: -5.9551
Max Act: 5.4551. Min Act: -0.1700
Data Index: 2689727 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9551. Min Range: -5.9551
Max Act: 5.4551. Min Act: -0.1700
Data Index: 7029180 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9551. Min Range: -5.9551
Max Act: 5.4863. Min Act: -0.1700
Data Index: 7130156 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9551. Min Range: -5.9551
Max Act: 5.4551. Min Act: -0.1700
Data Index: 8619163 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9551. Min Range: -5.9551
Max Act: 5.4238. Min Act: -0.1700
Data Index: 5703935 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9551. Min Range: -5.9551
Max Act: 5.4238. Min Act: -0.1700
Data Index: 6750542 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19