Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3385 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6098. Min Range: -2.6098
Max Act: 2.6098. Min Act: -0.1700
Data Index: 2413099 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6098. Min Range: -2.6098
Max Act: 2.5776. Min Act: -0.1700
Data Index: 3968476 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6098. Min Range: -2.6098
Max Act: 2.5291. Min Act: -0.1700
Data Index: 3033267 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6098. Min Range: -2.6098
Max Act: 2.5453. Min Act: -0.1700
Data Index: 951154 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6098. Min Range: -2.6098
Max Act: 2.5130. Min Act: -0.1700
Data Index: 2909517 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6098. Min Range: -2.6098
Max Act: 2.5130. Min Act: -0.1700
Data Index: 4588661 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6098. Min Range: -2.6098
Max Act: 2.4805. Min Act: -0.1700
Data Index: 3831667 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6098. Min Range: -2.6098
Max Act: 2.4805. Min Act: -0.1700
Data Index: 7154624 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6098. Min Range: -2.6098
Max Act: 2.4643. Min Act: -0.1700
Data Index: 5037836 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6098. Min Range: -2.6098
Max Act: 2.4643. Min Act: -0.1697
Data Index: 2655531 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6098. Min Range: -2.6098
Max Act: 2.4481. Min Act: -0.1700
Data Index: 2588475 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6098. Min Range: -2.6098
Max Act: 2.4481. Min Act: -0.1700
Data Index: 4243224 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6098. Min Range: -2.6098
Max Act: 2.4481. Min Act: -0.1700
Data Index: 4140509 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6098. Min Range: -2.6098
Max Act: 2.4155. Min Act: -0.1700
Data Index: 146372 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6098. Min Range: -2.6098
Max Act: 2.4155. Min Act: -0.1700
Data Index: 4069653 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6098. Min Range: -2.6098
Max Act: 2.4318. Min Act: -0.1700
Data Index: 3852083 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6098. Min Range: -2.6098
Max Act: 2.4481. Min Act: -0.1700
Data Index: 967417 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6098. Min Range: -2.6098
Max Act: 2.4318. Min Act: -0.1700
Data Index: 5621346 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6098. Min Range: -2.6098
Max Act: 2.4155. Min Act: -0.1700
Data Index: 2759263 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6098. Min Range: -2.6098
Max Act: 2.4155. Min Act: -0.1700
Data Index: 623235 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19