Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2451 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3031. Min Range: -7.3031
Max Act: 7.3031. Min Act: -0.1700
Data Index: 7875631 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3031. Min Range: -7.3031
Max Act: 6.8656. Min Act: -0.1700
Data Index: 5002026 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3031. Min Range: -7.3031
Max Act: 6.8656. Min Act: -0.1700
Data Index: 4033383 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3031. Min Range: -7.3031
Max Act: 6.8656. Min Act: -0.1700
Data Index: 119979 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3031. Min Range: -7.3031
Max Act: 6.8344. Min Act: -0.1700
Data Index: 8204956 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3031. Min Range: -7.3031
Max Act: 6.8344. Min Act: -0.1700
Data Index: 3322204 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3031. Min Range: -7.3031
Max Act: 6.8344. Min Act: -0.1700
Data Index: 5278704 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3031. Min Range: -7.3031
Max Act: 6.8031. Min Act: -0.1700
Data Index: 6574084 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3031. Min Range: -7.3031
Max Act: 6.8344. Min Act: -0.1700
Data Index: 6513358 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3031. Min Range: -7.3031
Max Act: 6.8031. Min Act: -0.1700
Data Index: 3500135 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3031. Min Range: -7.3031
Max Act: 6.8031. Min Act: -0.1700
Data Index: 171631 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3031. Min Range: -7.3031
Max Act: 6.8031. Min Act: -0.1700
Data Index: 3422330 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3031. Min Range: -7.3031
Max Act: 6.8031. Min Act: -0.1700
Data Index: 3414447 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3031. Min Range: -7.3031
Max Act: 6.7406. Min Act: -0.1700
Data Index: 779196 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3031. Min Range: -7.3031
Max Act: 6.7094. Min Act: -0.1700
Data Index: 3383331 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3031. Min Range: -7.3031
Max Act: 6.7094. Min Act: -0.1700
Data Index: 2273031 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3031. Min Range: -7.3031
Max Act: 6.6781. Min Act: -0.1700
Data Index: 6178224 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3031. Min Range: -7.3031
Max Act: 6.6781. Min Act: -0.1700
Data Index: 4524240 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3031. Min Range: -7.3031
Max Act: 6.6781. Min Act: -0.1700
Data Index: 7635504 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3031. Min Range: -7.3031
Max Act: 6.6781. Min Act: -0.1700
Data Index: 3224204 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19