Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5120 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4031. Min Range: -6.4031
Max Act: 6.4031. Min Act: -0.1700
Data Index: 6008873 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4031. Min Range: -6.4031
Max Act: 6.4031. Min Act: -0.1700
Data Index: 6008877 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4031. Min Range: -6.4031
Max Act: 6.1219. Min Act: -0.1700
Data Index: 3982973 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4031. Min Range: -6.4031
Max Act: 6.0906. Min Act: -0.1678
Data Index: 6008879 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4031. Min Range: -6.4031
Max Act: 5.9656. Min Act: -0.1700
Data Index: 5646036 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4031. Min Range: -6.4031
Max Act: 5.9344. Min Act: -0.1698
Data Index: 6008874 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4031. Min Range: -6.4031
Max Act: 5.9656. Min Act: -0.1700
Data Index: 3377453 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4031. Min Range: -6.4031
Max Act: 5.9344. Min Act: -0.1672
Data Index: 888128 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4031. Min Range: -6.4031
Max Act: 5.9031. Min Act: -0.1700
Data Index: 3383161 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4031. Min Range: -6.4031
Max Act: 5.8719. Min Act: -0.1700
Data Index: 7747512 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4031. Min Range: -6.4031
Max Act: 5.8719. Min Act: -0.1684
Data Index: 6008878 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4031. Min Range: -6.4031
Max Act: 5.8406. Min Act: -0.1700
Data Index: 357319 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4031. Min Range: -6.4031
Max Act: 5.8406. Min Act: -0.1700
Data Index: 68717 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4031. Min Range: -6.4031
Max Act: 5.8406. Min Act: -0.1700
Data Index: 7399077 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4031. Min Range: -6.4031
Max Act: 5.8094. Min Act: -0.1699
Data Index: 4083483 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4031. Min Range: -6.4031
Max Act: 5.8094. Min Act: -0.1700
Data Index: 6843044 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4031. Min Range: -6.4031
Max Act: 5.7781. Min Act: -0.1684
Data Index: 8291050 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4031. Min Range: -6.4031
Max Act: 5.7781. Min Act: -0.1700
Data Index: 6357366 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4031. Min Range: -6.4031
Max Act: 5.7469. Min Act: -0.1700
Data Index: 348310 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4031. Min Range: -6.4031
Max Act: 5.7469. Min Act: -0.1700
Data Index: 3475126 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19