Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3085 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9342. Min Range: -5.9342
Max Act: 5.9342. Min Act: -0.1700
Data Index: 476649 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9342. Min Range: -5.9342
Max Act: 5.9342. Min Act: -0.1700
Data Index: 3901538 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9342. Min Range: -5.9342
Max Act: 5.7780. Min Act: -0.1700
Data Index: 4431149 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9342. Min Range: -5.9342
Max Act: 5.6217. Min Act: -0.1700
Data Index: 4007255 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9342. Min Range: -5.9342
Max Act: 5.5905. Min Act: -0.1700
Data Index: 5917904 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9342. Min Range: -5.9342
Max Act: 5.5592. Min Act: -0.1700
Data Index: 112430 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9342. Min Range: -5.9342
Max Act: 5.5280. Min Act: -0.1700
Data Index: 3771163 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9342. Min Range: -5.9342
Max Act: 5.5280. Min Act: -0.1700
Data Index: 2995095 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9342. Min Range: -5.9342
Max Act: 5.5280. Min Act: -0.1700
Data Index: 4378408 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9342. Min Range: -5.9342
Max Act: 5.5280. Min Act: -0.1700
Data Index: 2598955 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9342. Min Range: -5.9342
Max Act: 5.5280. Min Act: -0.1700
Data Index: 3961412 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9342. Min Range: -5.9342
Max Act: 5.4967. Min Act: -0.1700
Data Index: 674431 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9342. Min Range: -5.9342
Max Act: 5.4967. Min Act: -0.1700
Data Index: 3228337 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9342. Min Range: -5.9342
Max Act: 5.4967. Min Act: -0.1700
Data Index: 2936864 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9342. Min Range: -5.9342
Max Act: 5.4342. Min Act: -0.1700
Data Index: 1841477 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9342. Min Range: -5.9342
Max Act: 5.4342. Min Act: -0.1700
Data Index: 2067379 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9342. Min Range: -5.9342
Max Act: 5.4342. Min Act: -0.1700
Data Index: 2120538 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9342. Min Range: -5.9342
Max Act: 5.4030. Min Act: -0.1700
Data Index: 2936575 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9342. Min Range: -5.9342
Max Act: 5.4030. Min Act: -0.1700
Data Index: 302439 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9342. Min Range: -5.9342
Max Act: 5.4030. Min Act: -0.1700
Data Index: 1276279 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19