Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 136 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2169. Min Range: -6.2169
Max Act: 6.2169. Min Act: -0.1700
Data Index: 7322603 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2169. Min Range: -6.2169
Max Act: 6.1232. Min Act: -0.1700
Data Index: 724223 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2169. Min Range: -6.2169
Max Act: 6.1232. Min Act: -0.1700
Data Index: 8048340 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2169. Min Range: -6.2169
Max Act: 6.1232. Min Act: -0.1700
Data Index: 2279474 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2169. Min Range: -6.2169
Max Act: 6.1232. Min Act: -0.1700
Data Index: 8083891 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2169. Min Range: -6.2169
Max Act: 6.0919. Min Act: -0.1700
Data Index: 5655417 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2169. Min Range: -6.2169
Max Act: 6.0919. Min Act: -0.1700
Data Index: 4602476 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2169. Min Range: -6.2169
Max Act: 6.0294. Min Act: -0.1700
Data Index: 7113503 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.9669. Min Act: -0.1700
Data Index: 857288 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.9982. Min Act: -0.1700
Data Index: 2086500 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.9669. Min Act: -0.1700
Data Index: 8770474 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.9044. Min Act: -0.1700
Data Index: 6560116 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.9357. Min Act: -0.1700
Data Index: 2203863 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.8732. Min Act: -0.1700
Data Index: 1764318 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.9044. Min Act: -0.1700
Data Index: 5327225 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.8732. Min Act: -0.1700
Data Index: 5440225 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.8732. Min Act: -0.1700
Data Index: 4520321 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.8732. Min Act: -0.1700
Data Index: 7104028 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.8419. Min Act: -0.1700
Data Index: 3532287 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.8107. Min Act: -0.1700
Data Index: 6625151 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19