Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 236 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5366. Min Range: -7.5366
Max Act: 7.5366. Min Act: -0.1700
Data Index: 3106432 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5366. Min Range: -7.5366
Max Act: 7.4428. Min Act: -0.1700
Data Index: 1502601 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5366. Min Range: -7.5366
Max Act: 7.4116. Min Act: -0.1700
Data Index: 7827015 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5366. Min Range: -7.5366
Max Act: 7.2866. Min Act: -0.1700
Data Index: 69748 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5366. Min Range: -7.5366
Max Act: 7.2553. Min Act: -0.1700
Data Index: 8738252 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5366. Min Range: -7.5366
Max Act: 7.2241. Min Act: -0.1700
Data Index: 7963415 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5366. Min Range: -7.5366
Max Act: 7.2241. Min Act: -0.1700
Data Index: 5744990 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5366. Min Range: -7.5366
Max Act: 7.1928. Min Act: -0.1700
Data Index: 1118061 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5366. Min Range: -7.5366
Max Act: 7.1616. Min Act: -0.1700
Data Index: 1204057 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5366. Min Range: -7.5366
Max Act: 7.1616. Min Act: -0.1700
Data Index: 2367561 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5366. Min Range: -7.5366
Max Act: 7.1303. Min Act: -0.1700
Data Index: 4168347 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5366. Min Range: -7.5366
Max Act: 7.0991. Min Act: -0.1700
Data Index: 3716230 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5366. Min Range: -7.5366
Max Act: 7.0991. Min Act: -0.1700
Data Index: 581794 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5366. Min Range: -7.5366
Max Act: 7.0991. Min Act: -0.1700
Data Index: 8034204 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5366. Min Range: -7.5366
Max Act: 7.0678. Min Act: -0.1700
Data Index: 7407241 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5366. Min Range: -7.5366
Max Act: 7.0678. Min Act: -0.1700
Data Index: 6558457 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5366. Min Range: -7.5366
Max Act: 7.0678. Min Act: -0.1700
Data Index: 6220668 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5366. Min Range: -7.5366
Max Act: 7.0366. Min Act: -0.1700
Data Index: 5798127 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5366. Min Range: -7.5366
Max Act: 7.0366. Min Act: -0.1700
Data Index: 2827619 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5366. Min Range: -7.5366
Max Act: 7.0366. Min Act: -0.1700
Data Index: 4510442 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19