Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4046 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1233. Min Range: -5.1233
Max Act: 5.1233. Min Act: -0.1700
Data Index: 2197842 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1233. Min Range: -5.1233
Max Act: 5.1233. Min Act: -0.1700
Data Index: 7626310 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1233. Min Range: -5.1233
Max Act: 4.9983. Min Act: -0.1700
Data Index: 1095204 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1233. Min Range: -5.1233
Max Act: 4.9983. Min Act: -0.1700
Data Index: 8301127 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1233. Min Range: -5.1233
Max Act: 4.8420. Min Act: -0.1700
Data Index: 4012096 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1233. Min Range: -5.1233
Max Act: 4.8420. Min Act: -0.1700
Data Index: 1231634 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1233. Min Range: -5.1233
Max Act: 4.8108. Min Act: -0.1700
Data Index: 7069364 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1233. Min Range: -5.1233
Max Act: 4.8108. Min Act: -0.1700
Data Index: 8301126 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1233. Min Range: -5.1233
Max Act: 4.7795. Min Act: -0.1700
Data Index: 2718361 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1233. Min Range: -5.1233
Max Act: 4.8108. Min Act: -0.1700
Data Index: 4131676 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1233. Min Range: -5.1233
Max Act: 4.8108. Min Act: -0.1700
Data Index: 4264411 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1233. Min Range: -5.1233
Max Act: 4.8108. Min Act: -0.1700
Data Index: 8143576 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1233. Min Range: -5.1233
Max Act: 4.7795. Min Act: -0.1700
Data Index: 511104 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1233. Min Range: -5.1233
Max Act: 4.8108. Min Act: -0.1700
Data Index: 2680968 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1233. Min Range: -5.1233
Max Act: 4.8108. Min Act: -0.1700
Data Index: 2806118 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1233. Min Range: -5.1233
Max Act: 4.8108. Min Act: -0.1700
Data Index: 126909 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1233. Min Range: -5.1233
Max Act: 4.7795. Min Act: -0.1700
Data Index: 338480 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1233. Min Range: -5.1233
Max Act: 4.7795. Min Act: -0.1700
Data Index: 6080368 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1233. Min Range: -5.1233
Max Act: 4.7483. Min Act: -0.1700
Data Index: 5610137 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1233. Min Range: -5.1233
Max Act: 4.7483. Min Act: -0.1700
Data Index: 8013557 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19