Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3267 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9255. Min Range: -6.9255
Max Act: 6.9255. Min Act: -0.1700
Data Index: 4378201 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9255. Min Range: -6.9255
Max Act: 6.8005. Min Act: -0.1700
Data Index: 5394993 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9255. Min Range: -6.9255
Max Act: 6.7380. Min Act: -0.1700
Data Index: 3126621 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9255. Min Range: -6.9255
Max Act: 6.5505. Min Act: -0.1700
Data Index: 6975125 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9255. Min Range: -6.9255
Max Act: 6.3630. Min Act: -0.1700
Data Index: 7497285 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9255. Min Range: -6.9255
Max Act: 6.3630. Min Act: -0.1700
Data Index: 2010982 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9255. Min Range: -6.9255
Max Act: 6.3630. Min Act: -0.1700
Data Index: 3687900 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9255. Min Range: -6.9255
Max Act: 6.3317. Min Act: -0.1700
Data Index: 2817 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9255. Min Range: -6.9255
Max Act: 6.3317. Min Act: -0.1700
Data Index: 6363418 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9255. Min Range: -6.9255
Max Act: 6.3317. Min Act: -0.1700
Data Index: 1302321 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9255. Min Range: -6.9255
Max Act: 6.3005. Min Act: -0.1700
Data Index: 4219571 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9255. Min Range: -6.9255
Max Act: 6.3005. Min Act: -0.1700
Data Index: 4407329 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9255. Min Range: -6.9255
Max Act: 6.2692. Min Act: -0.1700
Data Index: 5420153 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9255. Min Range: -6.9255
Max Act: 6.2692. Min Act: -0.1700
Data Index: 985521 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9255. Min Range: -6.9255
Max Act: 6.2380. Min Act: -0.1700
Data Index: 2480056 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9255. Min Range: -6.9255
Max Act: 6.2380. Min Act: -0.1700
Data Index: 8796758 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9255. Min Range: -6.9255
Max Act: 6.2380. Min Act: -0.1700
Data Index: 5035406 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9255. Min Range: -6.9255
Max Act: 6.2380. Min Act: -0.1700
Data Index: 7982365 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9255. Min Range: -6.9255
Max Act: 6.2380. Min Act: -0.1700
Data Index: 77593 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9255. Min Range: -6.9255
Max Act: 6.2380. Min Act: -0.1700
Data Index: 1590669 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19