Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5172 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3433. Min Range: -5.3433
Max Act: 5.3433. Min Act: -0.1700
Data Index: 2492833 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3433. Min Range: -5.3433
Max Act: 5.1871. Min Act: -0.1700
Data Index: 7481595 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3433. Min Range: -5.3433
Max Act: 4.7808. Min Act: -0.1700
Data Index: 7698316 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3433. Min Range: -5.3433
Max Act: 4.7496. Min Act: -0.1700
Data Index: 7698318 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3433. Min Range: -5.3433
Max Act: 4.7496. Min Act: -0.1700
Data Index: 7698317 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3433. Min Range: -5.3433
Max Act: 4.7183. Min Act: -0.1700
Data Index: 8490377 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3433. Min Range: -5.3433
Max Act: 4.6558. Min Act: -0.1700
Data Index: 8490380 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3433. Min Range: -5.3433
Max Act: 4.6246. Min Act: -0.1700
Data Index: 7698315 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3433. Min Range: -5.3433
Max Act: 4.5933. Min Act: -0.1700
Data Index: 7733097 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3433. Min Range: -5.3433
Max Act: 4.5621. Min Act: -0.1700
Data Index: 2462779 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3433. Min Range: -5.3433
Max Act: 4.5621. Min Act: -0.1700
Data Index: 4672653 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3433. Min Range: -5.3433
Max Act: 4.5621. Min Act: -0.1700
Data Index: 5909988 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3433. Min Range: -5.3433
Max Act: 4.5621. Min Act: -0.1700
Data Index: 1837994 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3433. Min Range: -5.3433
Max Act: 4.5933. Min Act: -0.1700
Data Index: 7780937 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3433. Min Range: -5.3433
Max Act: 4.5308. Min Act: -0.1700
Data Index: 8490381 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3433. Min Range: -5.3433
Max Act: 4.4683. Min Act: -0.1700
Data Index: 2408783 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3433. Min Range: -5.3433
Max Act: 4.4683. Min Act: -0.1700
Data Index: 252408 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3433. Min Range: -5.3433
Max Act: 4.4996. Min Act: -0.1700
Data Index: 6890725 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3433. Min Range: -5.3433
Max Act: 4.4996. Min Act: -0.1700
Data Index: 8578831 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3433. Min Range: -5.3433
Max Act: 4.5308. Min Act: -0.1700
Data Index: 2251914 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19