Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 851 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0803. Min Range: -6.0803
Max Act: 6.0490. Min Act: -0.1700
Data Index: 8731221 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0803. Min Range: -6.0803
Max Act: 6.0803. Min Act: -0.1700
Data Index: 6395137 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0803. Min Range: -6.0803
Max Act: 5.9553. Min Act: -0.1700
Data Index: 8034881 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0803. Min Range: -6.0803
Max Act: 5.9240. Min Act: -0.1700
Data Index: 3284040 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0803. Min Range: -6.0803
Max Act: 5.8928. Min Act: -0.1700
Data Index: 5352832 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0803. Min Range: -6.0803
Max Act: 5.8928. Min Act: -0.1700
Data Index: 5547110 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0803. Min Range: -6.0803
Max Act: 5.9240. Min Act: -0.1700
Data Index: 7312740 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0803. Min Range: -6.0803
Max Act: 5.8928. Min Act: -0.1700
Data Index: 3313530 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0803. Min Range: -6.0803
Max Act: 5.8928. Min Act: -0.1700
Data Index: 1986813 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0803. Min Range: -6.0803
Max Act: 5.8928. Min Act: -0.1700
Data Index: 430473 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0803. Min Range: -6.0803
Max Act: 5.8615. Min Act: -0.1700
Data Index: 3752327 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0803. Min Range: -6.0803
Max Act: 5.8615. Min Act: -0.1700
Data Index: 2021036 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0803. Min Range: -6.0803
Max Act: 5.8303. Min Act: -0.1700
Data Index: 5783096 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0803. Min Range: -6.0803
Max Act: 5.8303. Min Act: -0.1700
Data Index: 5798838 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0803. Min Range: -6.0803
Max Act: 5.8615. Min Act: -0.1700
Data Index: 2435007 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0803. Min Range: -6.0803
Max Act: 5.8303. Min Act: -0.1700
Data Index: 880414 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0803. Min Range: -6.0803
Max Act: 5.7990. Min Act: -0.1700
Data Index: 7381170 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0803. Min Range: -6.0803
Max Act: 5.7990. Min Act: -0.1700
Data Index: 1993632 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0803. Min Range: -6.0803
Max Act: 5.7990. Min Act: -0.1700
Data Index: 189064 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0803. Min Range: -6.0803
Max Act: 5.7365. Min Act: -0.1700
Data Index: 4546176 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19