Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3534 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7378. Min Range: -3.7378
Max Act: 3.7378. Min Act: -0.1700
Data Index: 873743 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7378. Min Range: -3.7378
Max Act: 3.6439. Min Act: -0.1700
Data Index: 7431918 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7378. Min Range: -3.7378
Max Act: 3.6126. Min Act: -0.1700
Data Index: 1763187 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7378. Min Range: -3.7378
Max Act: 3.5970. Min Act: -0.1700
Data Index: 6168194 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7378. Min Range: -3.7378
Max Act: 3.5813. Min Act: -0.1700
Data Index: 4101084 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7378. Min Range: -3.7378
Max Act: 3.5500. Min Act: -0.1700
Data Index: 7996710 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7378. Min Range: -3.7378
Max Act: 3.5500. Min Act: -0.1700
Data Index: 5533228 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7378. Min Range: -3.7378
Max Act: 3.5344. Min Act: -0.1700
Data Index: 3940979 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7378. Min Range: -3.7378
Max Act: 3.5031. Min Act: -0.1700
Data Index: 5587010 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7378. Min Range: -3.7378
Max Act: 3.4874. Min Act: -0.1700
Data Index: 8605962 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7378. Min Range: -3.7378
Max Act: 3.4874. Min Act: -0.1700
Data Index: 7796094 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7378. Min Range: -3.7378
Max Act: 3.4874. Min Act: -0.1700
Data Index: 5043997 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7378. Min Range: -3.7378
Max Act: 3.4561. Min Act: -0.1700
Data Index: 2441873 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7378. Min Range: -3.7378
Max Act: 3.4404. Min Act: -0.1700
Data Index: 4015698 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7378. Min Range: -3.7378
Max Act: 3.4404. Min Act: -0.1700
Data Index: 3186916 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7378. Min Range: -3.7378
Max Act: 3.4090. Min Act: -0.1700
Data Index: 5893079 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7378. Min Range: -3.7378
Max Act: 3.4247. Min Act: -0.1700
Data Index: 7058888 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7378. Min Range: -3.7378
Max Act: 3.4090. Min Act: -0.1700
Data Index: 5614275 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7378. Min Range: -3.7378
Max Act: 3.3777. Min Act: -0.1700
Data Index: 7907270 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7378. Min Range: -3.7378
Max Act: 3.3620. Min Act: -0.1700
Data Index: 3871261 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19