Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 168 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2489. Min Range: -8.2489
Max Act: 8.2489. Min Act: -0.1700
Data Index: 5229517 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2489. Min Range: -8.2489
Max Act: 8.1864. Min Act: -0.1700
Data Index: 4851092 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2489. Min Range: -8.2489
Max Act: 7.9364. Min Act: -0.1700
Data Index: 7407620 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2489. Min Range: -8.2489
Max Act: 7.8739. Min Act: -0.1700
Data Index: 1163237 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2489. Min Range: -8.2489
Max Act: 7.8426. Min Act: -0.1700
Data Index: 3745985 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2489. Min Range: -8.2489
Max Act: 7.8426. Min Act: -0.1700
Data Index: 8830064 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2489. Min Range: -8.2489
Max Act: 7.7176. Min Act: -0.1700
Data Index: 7669857 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2489. Min Range: -8.2489
Max Act: 7.7176. Min Act: -0.1700
Data Index: 7280023 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2489. Min Range: -8.2489
Max Act: 7.7176. Min Act: -0.1700
Data Index: 4642351 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2489. Min Range: -8.2489
Max Act: 7.6864. Min Act: -0.1700
Data Index: 75041 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2489. Min Range: -8.2489
Max Act: 7.6864. Min Act: -0.1700
Data Index: 3177234 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2489. Min Range: -8.2489
Max Act: 7.6864. Min Act: -0.1700
Data Index: 6104668 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2489. Min Range: -8.2489
Max Act: 7.6864. Min Act: -0.1700
Data Index: 6109645 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2489. Min Range: -8.2489
Max Act: 7.6551. Min Act: -0.1700
Data Index: 5670443 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2489. Min Range: -8.2489
Max Act: 7.6239. Min Act: -0.1700
Data Index: 5840888 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2489. Min Range: -8.2489
Max Act: 7.5926. Min Act: -0.1700
Data Index: 191828 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2489. Min Range: -8.2489
Max Act: 7.5614. Min Act: -0.1700
Data Index: 4753256 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2489. Min Range: -8.2489
Max Act: 7.5614. Min Act: -0.1700
Data Index: 8219666 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2489. Min Range: -8.2489
Max Act: 7.4989. Min Act: -0.1700
Data Index: 1251895 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2489. Min Range: -8.2489
Max Act: 7.5301. Min Act: -0.1700
Data Index: 7188350 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19