Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5453 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9107. Min Range: -2.9107
Max Act: 2.9107. Min Act: -0.1700
Data Index: 6893182 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9107. Min Range: -2.9107
Max Act: 2.9107. Min Act: -0.1700
Data Index: 5625045 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9107. Min Range: -2.9107
Max Act: 2.9107. Min Act: -0.1700
Data Index: 7473625 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9107. Min Range: -2.9107
Max Act: 2.8790. Min Act: -0.1700
Data Index: 7395924 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9107. Min Range: -2.9107
Max Act: 2.8790. Min Act: -0.1700
Data Index: 6518200 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9107. Min Range: -2.9107
Max Act: 2.8790. Min Act: -0.1700
Data Index: 4416221 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9107. Min Range: -2.9107
Max Act: 2.8472. Min Act: -0.1700
Data Index: 2048336 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9107. Min Range: -2.9107
Max Act: 2.8472. Min Act: -0.1700
Data Index: 2124199 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9107. Min Range: -2.9107
Max Act: 2.8313. Min Act: -0.1700
Data Index: 5970124 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9107. Min Range: -2.9107
Max Act: 2.8154. Min Act: -0.1700
Data Index: 8486989 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9107. Min Range: -2.9107
Max Act: 2.8154. Min Act: -0.1700
Data Index: 1322479 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9107. Min Range: -2.9107
Max Act: 2.7995. Min Act: -0.1700
Data Index: 2624988 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9107. Min Range: -2.9107
Max Act: 2.7995. Min Act: -0.1700
Data Index: 3136143 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9107. Min Range: -2.9107
Max Act: 2.8154. Min Act: -0.1700
Data Index: 3422383 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9107. Min Range: -2.9107
Max Act: 2.7995. Min Act: -0.1700
Data Index: 1196194 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9107. Min Range: -2.9107
Max Act: 2.7995. Min Act: -0.1700
Data Index: 8486977 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9107. Min Range: -2.9107
Max Act: 2.8154. Min Act: -0.1700
Data Index: 7079254 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9107. Min Range: -2.9107
Max Act: 2.7995. Min Act: -0.1700
Data Index: 4373422 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9107. Min Range: -2.9107
Max Act: 2.7676. Min Act: -0.1700
Data Index: 2946713 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9107. Min Range: -2.9107
Max Act: 2.7835. Min Act: -0.1700
Data Index: 3152978 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19