Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3594 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.2292. Min Range: -14.2292
Max Act: 14.2292. Min Act: -0.1700
Data Index: 2188089 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.2292. Min Range: -14.2292
Max Act: 14.1042. Min Act: -0.1700
Data Index: 6285443 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.2292. Min Range: -14.2292
Max Act: 13.5417. Min Act: -0.1700
Data Index: 3797881 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.2292. Min Range: -14.2292
Max Act: 13.3542. Min Act: -0.1700
Data Index: 4973988 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.2292. Min Range: -14.2292
Max Act: 13.3542. Min Act: -0.1700
Data Index: 829129 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.2292. Min Range: -14.2292
Max Act: 13.2917. Min Act: -0.1700
Data Index: 5544091 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.2292. Min Range: -14.2292
Max Act: 13.2917. Min Act: -0.1700
Data Index: 3424964 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.2292. Min Range: -14.2292
Max Act: 13.1042. Min Act: -0.1700
Data Index: 2346852 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.2292. Min Range: -14.2292
Max Act: 13.1042. Min Act: -0.1700
Data Index: 3895706 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.2292. Min Range: -14.2292
Max Act: 13.1042. Min Act: -0.1700
Data Index: 3404649 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.2292. Min Range: -14.2292
Max Act: 13.1042. Min Act: -0.1700
Data Index: 6855787 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.2292. Min Range: -14.2292
Max Act: 12.9167. Min Act: -0.1700
Data Index: 7624816 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.2292. Min Range: -14.2292
Max Act: 12.8542. Min Act: -0.1700
Data Index: 3209947 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.2292. Min Range: -14.2292
Max Act: 12.8542. Min Act: -0.1700
Data Index: 8645136 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.2292. Min Range: -14.2292
Max Act: 12.8542. Min Act: -0.1700
Data Index: 5544090 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.2292. Min Range: -14.2292
Max Act: 12.8542. Min Act: -0.1700
Data Index: 6159493 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.2292. Min Range: -14.2292
Max Act: 12.8542. Min Act: -0.1700
Data Index: 6848633 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.2292. Min Range: -14.2292
Max Act: 12.7917. Min Act: -0.1700
Data Index: 2707882 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.2292. Min Range: -14.2292
Max Act: 12.8542. Min Act: -0.1700
Data Index: 8169730 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.2292. Min Range: -14.2292
Max Act: 12.7292. Min Act: -0.1700
Data Index: 1140089 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19