Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2451 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4962. Min Range: -11.4962
Max Act: 11.4962. Min Act: -0.1700
Data Index: 7358988 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4962. Min Range: -11.4962
Max Act: 11.4962. Min Act: -0.1700
Data Index: 5178587 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4962. Min Range: -11.4962
Max Act: 11.4337. Min Act: -0.1700
Data Index: 4667441 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4962. Min Range: -11.4962
Max Act: 11.3712. Min Act: -0.1700
Data Index: 8407947 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4962. Min Range: -11.4962
Max Act: 11.3712. Min Act: -0.1700
Data Index: 2670947 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4962. Min Range: -11.4962
Max Act: 11.3712. Min Act: -0.1700
Data Index: 2357248 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4962. Min Range: -11.4962
Max Act: 11.3712. Min Act: -0.1700
Data Index: 7238182 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4962. Min Range: -11.4962
Max Act: 11.3712. Min Act: -0.1700
Data Index: 1674308 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4962. Min Range: -11.4962
Max Act: 11.3712. Min Act: -0.1700
Data Index: 6357353 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4962. Min Range: -11.4962
Max Act: 11.3712. Min Act: -0.1700
Data Index: 6330323 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4962. Min Range: -11.4962
Max Act: 11.3712. Min Act: -0.1700
Data Index: 218025 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4962. Min Range: -11.4962
Max Act: 11.3712. Min Act: -0.1700
Data Index: 5810458 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4962. Min Range: -11.4962
Max Act: 11.3712. Min Act: -0.1700
Data Index: 4158135 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4962. Min Range: -11.4962
Max Act: 11.3087. Min Act: -0.1700
Data Index: 4520290 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4962. Min Range: -11.4962
Max Act: 11.3087. Min Act: -0.1700
Data Index: 7598222 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4962. Min Range: -11.4962
Max Act: 11.2462. Min Act: -0.1700
Data Index: 8670742 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4962. Min Range: -11.4962
Max Act: 11.2462. Min Act: -0.1700
Data Index: 2277935 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4962. Min Range: -11.4962
Max Act: 11.1837. Min Act: -0.1700
Data Index: 3215461 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4962. Min Range: -11.4962
Max Act: 11.1837. Min Act: -0.1700
Data Index: 7256810 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4962. Min Range: -11.4962
Max Act: 11.1837. Min Act: -0.1700
Data Index: 7916832 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19