Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3051 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9356. Min Range: -5.9356
Max Act: 5.9356. Min Act: -0.1700
Data Index: 939507 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9356. Min Range: -5.9356
Max Act: 5.8106. Min Act: -0.1700
Data Index: 1259927 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9356. Min Range: -5.9356
Max Act: 5.7793. Min Act: -0.1700
Data Index: 1940370 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9356. Min Range: -5.9356
Max Act: 5.7481. Min Act: -0.1700
Data Index: 3985635 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9356. Min Range: -5.9356
Max Act: 5.7168. Min Act: -0.1700
Data Index: 4637370 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9356. Min Range: -5.9356
Max Act: 5.6231. Min Act: -0.1700
Data Index: 3942273 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9356. Min Range: -5.9356
Max Act: 5.5918. Min Act: -0.1700
Data Index: 5736979 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9356. Min Range: -5.9356
Max Act: 5.5606. Min Act: -0.1700
Data Index: 4268736 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9356. Min Range: -5.9356
Max Act: 5.5606. Min Act: -0.1700
Data Index: 3798255 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9356. Min Range: -5.9356
Max Act: 5.5293. Min Act: -0.1700
Data Index: 2705711 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9356. Min Range: -5.9356
Max Act: 5.5293. Min Act: -0.1700
Data Index: 4496616 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9356. Min Range: -5.9356
Max Act: 5.5293. Min Act: -0.1700
Data Index: 1781166 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9356. Min Range: -5.9356
Max Act: 5.5293. Min Act: -0.1700
Data Index: 4914274 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9356. Min Range: -5.9356
Max Act: 5.5293. Min Act: -0.1700
Data Index: 3235587 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9356. Min Range: -5.9356
Max Act: 5.4981. Min Act: -0.1700
Data Index: 6999224 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9356. Min Range: -5.9356
Max Act: 5.4981. Min Act: -0.1700
Data Index: 425159 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9356. Min Range: -5.9356
Max Act: 5.4981. Min Act: -0.1700
Data Index: 3905095 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9356. Min Range: -5.9356
Max Act: 5.4981. Min Act: -0.1700
Data Index: 6018437 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9356. Min Range: -5.9356
Max Act: 5.4668. Min Act: -0.1700
Data Index: 5469548 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9356. Min Range: -5.9356
Max Act: 5.4356. Min Act: -0.1700
Data Index: 3284149 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19