Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3494 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3892. Min Range: -8.3892
Max Act: 8.3892. Min Act: -0.1700
Data Index: 402431 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3892. Min Range: -8.3892
Max Act: 8.3580. Min Act: -0.1700
Data Index: 6164427 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3892. Min Range: -8.3892
Max Act: 8.0767. Min Act: -0.1700
Data Index: 7959883 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3892. Min Range: -8.3892
Max Act: 8.0767. Min Act: -0.1700
Data Index: 6127573 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3892. Min Range: -8.3892
Max Act: 8.0142. Min Act: -0.1700
Data Index: 6967192 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3892. Min Range: -8.3892
Max Act: 8.0142. Min Act: -0.1700
Data Index: 8362493 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3892. Min Range: -8.3892
Max Act: 7.8892. Min Act: -0.1700
Data Index: 4108479 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3892. Min Range: -8.3892
Max Act: 7.8580. Min Act: -0.1700
Data Index: 7959884 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3892. Min Range: -8.3892
Max Act: 7.8580. Min Act: -0.1700
Data Index: 3520762 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3892. Min Range: -8.3892
Max Act: 7.8580. Min Act: -0.1700
Data Index: 4732018 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3892. Min Range: -8.3892
Max Act: 7.8267. Min Act: -0.1700
Data Index: 3687290 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3892. Min Range: -8.3892
Max Act: 7.7955. Min Act: -0.1700
Data Index: 7776629 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3892. Min Range: -8.3892
Max Act: 7.7642. Min Act: -0.1700
Data Index: 6786440 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3892. Min Range: -8.3892
Max Act: 7.7642. Min Act: -0.1700
Data Index: 2999107 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3892. Min Range: -8.3892
Max Act: 7.6705. Min Act: -0.1700
Data Index: 241995 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3892. Min Range: -8.3892
Max Act: 7.6392. Min Act: -0.1700
Data Index: 3030369 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3892. Min Range: -8.3892
Max Act: 7.5767. Min Act: -0.1699
Data Index: 6269073 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3892. Min Range: -8.3892
Max Act: 7.6080. Min Act: -0.1700
Data Index: 8331147 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3892. Min Range: -8.3892
Max Act: 7.5767. Min Act: -0.1700
Data Index: 7733021 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3892. Min Range: -8.3892
Max Act: 7.5455. Min Act: -0.1700
Data Index: 5550382 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19