Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3539 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3464. Min Range: -7.3464
Max Act: 7.3464. Min Act: -0.1700
Data Index: 682998 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3464. Min Range: -7.3464
Max Act: 6.9714. Min Act: -0.1700
Data Index: 7615881 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3464. Min Range: -7.3464
Max Act: 6.9089. Min Act: -0.1700
Data Index: 2841727 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3464. Min Range: -7.3464
Max Act: 6.8152. Min Act: -0.1700
Data Index: 8075569 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3464. Min Range: -7.3464
Max Act: 6.8152. Min Act: -0.1700
Data Index: 5910463 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3464. Min Range: -7.3464
Max Act: 6.8152. Min Act: -0.1700
Data Index: 5469301 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3464. Min Range: -7.3464
Max Act: 6.7839. Min Act: -0.1700
Data Index: 6454223 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3464. Min Range: -7.3464
Max Act: 6.7527. Min Act: -0.1700
Data Index: 2985462 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3464. Min Range: -7.3464
Max Act: 6.7527. Min Act: -0.1700
Data Index: 7110357 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3464. Min Range: -7.3464
Max Act: 6.7214. Min Act: -0.1700
Data Index: 2339267 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3464. Min Range: -7.3464
Max Act: 6.7214. Min Act: -0.1700
Data Index: 1233044 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3464. Min Range: -7.3464
Max Act: 6.7214. Min Act: -0.1700
Data Index: 5020795 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3464. Min Range: -7.3464
Max Act: 6.7214. Min Act: -0.1700
Data Index: 5467704 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3464. Min Range: -7.3464
Max Act: 6.6902. Min Act: -0.1700
Data Index: 6528554 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3464. Min Range: -7.3464
Max Act: 6.6589. Min Act: -0.1700
Data Index: 2890590 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3464. Min Range: -7.3464
Max Act: 6.6589. Min Act: -0.1700
Data Index: 1860213 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3464. Min Range: -7.3464
Max Act: 6.6589. Min Act: -0.1700
Data Index: 8403289 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3464. Min Range: -7.3464
Max Act: 6.6589. Min Act: -0.1700
Data Index: 379610 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3464. Min Range: -7.3464
Max Act: 6.6277. Min Act: -0.1700
Data Index: 7400089 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3464. Min Range: -7.3464
Max Act: 6.6277. Min Act: -0.1700
Data Index: 5127793 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19