Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2025 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6333. Min Range: -2.6333
Max Act: 2.6333. Min Act: -0.1700
Data Index: 1132668 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6333. Min Range: -2.6333
Max Act: 2.6333. Min Act: -0.1700
Data Index: 8526997 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6333. Min Range: -2.6333
Max Act: 2.6172. Min Act: -0.1700
Data Index: 6819269 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6333. Min Range: -2.6333
Max Act: 2.6172. Min Act: -0.1700
Data Index: 6819267 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6333. Min Range: -2.6333
Max Act: 2.6011. Min Act: -0.1700
Data Index: 7249876 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6333. Min Range: -2.6333
Max Act: 2.5850. Min Act: -0.1700
Data Index: 1838642 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6333. Min Range: -2.6333
Max Act: 2.6011. Min Act: -0.1700
Data Index: 8544331 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6333. Min Range: -2.6333
Max Act: 2.5689. Min Act: -0.1700
Data Index: 6418571 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6333. Min Range: -2.6333
Max Act: 2.5689. Min Act: -0.1700
Data Index: 2400633 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6333. Min Range: -2.6333
Max Act: 2.5689. Min Act: -0.1700
Data Index: 2130175 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6333. Min Range: -2.6333
Max Act: 2.5528. Min Act: -0.1700
Data Index: 7549456 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6333. Min Range: -2.6333
Max Act: 2.5205. Min Act: -0.1700
Data Index: 6819271 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6333. Min Range: -2.6333
Max Act: 2.5366. Min Act: -0.1700
Data Index: 7542891 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6333. Min Range: -2.6333
Max Act: 2.5366. Min Act: -0.1700
Data Index: 2400626 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6333. Min Range: -2.6333
Max Act: 2.5528. Min Act: -0.1700
Data Index: 4848761 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6333. Min Range: -2.6333
Max Act: 2.5366. Min Act: -0.1700
Data Index: 5511816 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6333. Min Range: -2.6333
Max Act: 2.5366. Min Act: -0.1700
Data Index: 3964896 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6333. Min Range: -2.6333
Max Act: 2.5528. Min Act: -0.1700
Data Index: 7918378 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6333. Min Range: -2.6333
Max Act: 2.5205. Min Act: -0.1700
Data Index: 3408386 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6333. Min Range: -2.6333
Max Act: 2.5205. Min Act: -0.1700
Data Index: 2690257 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19