Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1532 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5505. Min Range: -5.5505
Max Act: 5.5505. Min Act: -0.1700
Data Index: 1904520 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5505. Min Range: -5.5505
Max Act: 5.1443. Min Act: -0.1700
Data Index: 2057151 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5505. Min Range: -5.5505
Max Act: 5.1130. Min Act: -0.1700
Data Index: 1348138 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5505. Min Range: -5.5505
Max Act: 5.0818. Min Act: -0.1700
Data Index: 6755130 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5505. Min Range: -5.5505
Max Act: 5.0818. Min Act: -0.1700
Data Index: 1896102 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5505. Min Range: -5.5505
Max Act: 5.0505. Min Act: -0.1700
Data Index: 4431728 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5505. Min Range: -5.5505
Max Act: 5.0193. Min Act: -0.1700
Data Index: 593246 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5505. Min Range: -5.5505
Max Act: 5.0193. Min Act: -0.1700
Data Index: 7652528 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5505. Min Range: -5.5505
Max Act: 4.9880. Min Act: -0.1700
Data Index: 561598 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5505. Min Range: -5.5505
Max Act: 4.9880. Min Act: -0.1700
Data Index: 741332 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5505. Min Range: -5.5505
Max Act: 4.9880. Min Act: -0.1700
Data Index: 6789308 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5505. Min Range: -5.5505
Max Act: 4.9880. Min Act: -0.1700
Data Index: 6287696 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5505. Min Range: -5.5505
Max Act: 4.9568. Min Act: -0.1700
Data Index: 7301683 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5505. Min Range: -5.5505
Max Act: 4.9255. Min Act: -0.1700
Data Index: 3290763 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5505. Min Range: -5.5505
Max Act: 4.9568. Min Act: -0.1700
Data Index: 1589811 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5505. Min Range: -5.5505
Max Act: 4.9568. Min Act: -0.1700
Data Index: 2251005 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5505. Min Range: -5.5505
Max Act: 4.9255. Min Act: -0.1700
Data Index: 6893440 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5505. Min Range: -5.5505
Max Act: 4.9255. Min Act: -0.1700
Data Index: 1819892 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5505. Min Range: -5.5505
Max Act: 4.9255. Min Act: -0.1700
Data Index: 3638369 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5505. Min Range: -5.5505
Max Act: 4.9255. Min Act: -0.1700
Data Index: 5793416 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19