Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2178 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.8055. Min Range: -7.8055
Max Act: 7.8055. Min Act: -0.1700
Data Index: 1634468 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8055. Min Range: -7.8055
Max Act: 7.5242. Min Act: -0.1700
Data Index: 2936632 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8055. Min Range: -7.8055
Max Act: 7.5555. Min Act: -0.1700
Data Index: 6192090 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8055. Min Range: -7.8055
Max Act: 7.5242. Min Act: -0.1700
Data Index: 5679895 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8055. Min Range: -7.8055
Max Act: 7.4617. Min Act: -0.1700
Data Index: 5120251 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8055. Min Range: -7.8055
Max Act: 7.4305. Min Act: -0.1700
Data Index: 6049163 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8055. Min Range: -7.8055
Max Act: 7.4305. Min Act: -0.1700
Data Index: 456726 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8055. Min Range: -7.8055
Max Act: 7.3680. Min Act: -0.1700
Data Index: 598619 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8055. Min Range: -7.8055
Max Act: 7.3367. Min Act: -0.1700
Data Index: 4090664 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8055. Min Range: -7.8055
Max Act: 7.2742. Min Act: -0.1700
Data Index: 6959798 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8055. Min Range: -7.8055
Max Act: 7.2430. Min Act: -0.1700
Data Index: 10750 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8055. Min Range: -7.8055
Max Act: 7.1805. Min Act: -0.1700
Data Index: 3733517 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8055. Min Range: -7.8055
Max Act: 7.1805. Min Act: -0.1700
Data Index: 4278620 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8055. Min Range: -7.8055
Max Act: 7.1492. Min Act: -0.1700
Data Index: 1163769 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8055. Min Range: -7.8055
Max Act: 7.1492. Min Act: -0.1700
Data Index: 158428 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8055. Min Range: -7.8055
Max Act: 7.1492. Min Act: -0.1700
Data Index: 6872437 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8055. Min Range: -7.8055
Max Act: 7.0867. Min Act: -0.1700
Data Index: 6589857 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8055. Min Range: -7.8055
Max Act: 7.1180. Min Act: -0.1700
Data Index: 8145603 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8055. Min Range: -7.8055
Max Act: 7.1180. Min Act: -0.1700
Data Index: 4633643 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8055. Min Range: -7.8055
Max Act: 7.0867. Min Act: -0.1700
Data Index: 6721031 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19