Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5254 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3038. Min Range: -8.3038
Max Act: 8.3038. Min Act: -0.1700
Data Index: 4749169 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3038. Min Range: -8.3038
Max Act: 7.9288. Min Act: -0.1700
Data Index: 4567789 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3038. Min Range: -8.3038
Max Act: 7.9288. Min Act: -0.1700
Data Index: 869352 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3038. Min Range: -8.3038
Max Act: 7.8976. Min Act: -0.1700
Data Index: 741924 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3038. Min Range: -8.3038
Max Act: 7.7726. Min Act: -0.1700
Data Index: 1476117 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3038. Min Range: -8.3038
Max Act: 7.7413. Min Act: -0.1700
Data Index: 3073623 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3038. Min Range: -8.3038
Max Act: 7.5851. Min Act: -0.1700
Data Index: 6601176 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3038. Min Range: -8.3038
Max Act: 7.5851. Min Act: -0.1700
Data Index: 4990480 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3038. Min Range: -8.3038
Max Act: 7.5538. Min Act: -0.1700
Data Index: 4964519 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3038. Min Range: -8.3038
Max Act: 7.4913. Min Act: -0.1700
Data Index: 2284380 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3038. Min Range: -8.3038
Max Act: 7.4913. Min Act: -0.1700
Data Index: 1039827 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3038. Min Range: -8.3038
Max Act: 7.4601. Min Act: -0.1700
Data Index: 4235882 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3038. Min Range: -8.3038
Max Act: 7.4288. Min Act: -0.1700
Data Index: 299661 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3038. Min Range: -8.3038
Max Act: 7.4288. Min Act: -0.1700
Data Index: 1085404 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3038. Min Range: -8.3038
Max Act: 7.4288. Min Act: -0.1700
Data Index: 8263747 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3038. Min Range: -8.3038
Max Act: 7.3976. Min Act: -0.1700
Data Index: 1382084 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3038. Min Range: -8.3038
Max Act: 7.3663. Min Act: -0.1700
Data Index: 1014456 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3038. Min Range: -8.3038
Max Act: 7.3038. Min Act: -0.1700
Data Index: 7913477 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3038. Min Range: -8.3038
Max Act: 7.3351. Min Act: -0.1700
Data Index: 8044491 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3038. Min Range: -8.3038
Max Act: 7.3351. Min Act: -0.1700
Data Index: 8534911 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19