Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5421 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7367. Min Range: -3.7367
Max Act: 3.7367. Min Act: -0.1700
Data Index: 8595055 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7367. Min Range: -3.7367
Max Act: 3.6898. Min Act: -0.1700
Data Index: 5109728 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7367. Min Range: -3.7367
Max Act: 3.6585. Min Act: -0.1700
Data Index: 3385199 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7367. Min Range: -3.7367
Max Act: 3.5802. Min Act: -0.1700
Data Index: 608698 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7367. Min Range: -3.7367
Max Act: 3.5802. Min Act: -0.1700
Data Index: 2751451 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7367. Min Range: -3.7367
Max Act: 3.5646. Min Act: -0.1700
Data Index: 1595307 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7367. Min Range: -3.7367
Max Act: 3.5646. Min Act: -0.1700
Data Index: 5921690 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7367. Min Range: -3.7367
Max Act: 3.5802. Min Act: -0.1700
Data Index: 1852064 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7367. Min Range: -3.7367
Max Act: 3.5489. Min Act: -0.1700
Data Index: 4121111 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7367. Min Range: -3.7367
Max Act: 3.5489. Min Act: -0.1700
Data Index: 6151824 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7367. Min Range: -3.7367
Max Act: 3.5333. Min Act: -0.1700
Data Index: 4050853 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7367. Min Range: -3.7367
Max Act: 3.5489. Min Act: -0.1700
Data Index: 6416365 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7367. Min Range: -3.7367
Max Act: 3.5176. Min Act: -0.1700
Data Index: 209308 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7367. Min Range: -3.7367
Max Act: 3.5333. Min Act: -0.1700
Data Index: 5492956 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7367. Min Range: -3.7367
Max Act: 3.5333. Min Act: -0.1700
Data Index: 5396313 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7367. Min Range: -3.7367
Max Act: 3.5019. Min Act: -0.1700
Data Index: 990868 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7367. Min Range: -3.7367
Max Act: 3.5333. Min Act: -0.1700
Data Index: 3026480 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7367. Min Range: -3.7367
Max Act: 3.5176. Min Act: -0.1700
Data Index: 7951385 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7367. Min Range: -3.7367
Max Act: 3.5176. Min Act: -0.1700
Data Index: 5763443 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7367. Min Range: -3.7367
Max Act: 3.5176. Min Act: -0.1700
Data Index: 608692 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19