Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4978 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2343. Min Range: -5.2343
Max Act: 5.2343. Min Act: -0.1700
Data Index: 3969321 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2343. Min Range: -5.2343
Max Act: 5.1718. Min Act: -0.1700
Data Index: 4377948 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2343. Min Range: -5.2343
Max Act: 5.1405. Min Act: -0.1700
Data Index: 1840128 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2343. Min Range: -5.2343
Max Act: 5.1405. Min Act: -0.1700
Data Index: 7504219 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2343. Min Range: -5.2343
Max Act: 5.1093. Min Act: -0.1700
Data Index: 1637520 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2343. Min Range: -5.2343
Max Act: 5.0468. Min Act: -0.1700
Data Index: 1576201 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2343. Min Range: -5.2343
Max Act: 5.0780. Min Act: -0.1700
Data Index: 5228907 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2343. Min Range: -5.2343
Max Act: 5.0780. Min Act: -0.1700
Data Index: 2220521 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2343. Min Range: -5.2343
Max Act: 5.0155. Min Act: -0.1700
Data Index: 5985071 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2343. Min Range: -5.2343
Max Act: 5.0468. Min Act: -0.1700
Data Index: 5495449 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2343. Min Range: -5.2343
Max Act: 5.0468. Min Act: -0.1700
Data Index: 7562328 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2343. Min Range: -5.2343
Max Act: 5.0468. Min Act: -0.1700
Data Index: 7468151 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2343. Min Range: -5.2343
Max Act: 4.9530. Min Act: -0.1700
Data Index: 1562307 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2343. Min Range: -5.2343
Max Act: 4.9843. Min Act: -0.1700
Data Index: 5322406 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2343. Min Range: -5.2343
Max Act: 4.9530. Min Act: -0.1700
Data Index: 1550866 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2343. Min Range: -5.2343
Max Act: 4.9530. Min Act: -0.1700
Data Index: 5578560 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2343. Min Range: -5.2343
Max Act: 4.9530. Min Act: -0.1700
Data Index: 6457422 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2343. Min Range: -5.2343
Max Act: 4.9218. Min Act: -0.1700
Data Index: 8716064 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2343. Min Range: -5.2343
Max Act: 4.8905. Min Act: -0.1700
Data Index: 2000071 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2343. Min Range: -5.2343
Max Act: 4.8905. Min Act: -0.1700
Data Index: 7732927 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19