Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3025 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7122. Min Range: -5.7122
Max Act: 5.7122. Min Act: -0.1700
Data Index: 1460606 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7122. Min Range: -5.7122
Max Act: 5.6497. Min Act: -0.1700
Data Index: 1690680 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7122. Min Range: -5.7122
Max Act: 5.6185. Min Act: -0.1700
Data Index: 2554077 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7122. Min Range: -5.7122
Max Act: 5.6185. Min Act: -0.1694
Data Index: 7646167 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7122. Min Range: -5.7122
Max Act: 5.6185. Min Act: -0.1700
Data Index: 4386996 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7122. Min Range: -5.7122
Max Act: 5.5560. Min Act: -0.1700
Data Index: 5906396 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7122. Min Range: -5.7122
Max Act: 5.4935. Min Act: -0.1700
Data Index: 5078187 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7122. Min Range: -5.7122
Max Act: 5.5247. Min Act: -0.1700
Data Index: 8596982 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7122. Min Range: -5.7122
Max Act: 5.4935. Min Act: -0.1700
Data Index: 7250443 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7122. Min Range: -5.7122
Max Act: 5.4935. Min Act: -0.1699
Data Index: 3312480 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7122. Min Range: -5.7122
Max Act: 5.4935. Min Act: -0.1700
Data Index: 2832096 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7122. Min Range: -5.7122
Max Act: 5.4622. Min Act: -0.1700
Data Index: 1804634 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7122. Min Range: -5.7122
Max Act: 5.4310. Min Act: -0.1700
Data Index: 683020 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7122. Min Range: -5.7122
Max Act: 5.4310. Min Act: -0.1700
Data Index: 5750601 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7122. Min Range: -5.7122
Max Act: 5.4310. Min Act: -0.1700
Data Index: 8741808 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7122. Min Range: -5.7122
Max Act: 5.3997. Min Act: -0.1700
Data Index: 7080152 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7122. Min Range: -5.7122
Max Act: 5.3997. Min Act: -0.1700
Data Index: 8425187 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7122. Min Range: -5.7122
Max Act: 5.3997. Min Act: -0.1700
Data Index: 1138331 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7122. Min Range: -5.7122
Max Act: 5.3685. Min Act: -0.1700
Data Index: 1613912 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7122. Min Range: -5.7122
Max Act: 5.3685. Min Act: -0.1698
Data Index: 3438499 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19