Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3522 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6481. Min Range: -6.6481
Max Act: 6.6481. Min Act: -0.1698
Data Index: 114210 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6481. Min Range: -6.6481
Max Act: 6.4918. Min Act: -0.1700
Data Index: 5611914 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6481. Min Range: -6.6481
Max Act: 6.3668. Min Act: -0.1700
Data Index: 1074063 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6481. Min Range: -6.6481
Max Act: 6.3356. Min Act: -0.1700
Data Index: 7947414 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6481. Min Range: -6.6481
Max Act: 6.2731. Min Act: -0.1700
Data Index: 8270821 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6481. Min Range: -6.6481
Max Act: 6.2418. Min Act: -0.1700
Data Index: 7962842 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6481. Min Range: -6.6481
Max Act: 6.2418. Min Act: -0.1700
Data Index: 4214566 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6481. Min Range: -6.6481
Max Act: 6.2418. Min Act: -0.1700
Data Index: 7707927 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6481. Min Range: -6.6481
Max Act: 6.2106. Min Act: -0.1700
Data Index: 5023089 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6481. Min Range: -6.6481
Max Act: 6.2106. Min Act: -0.1700
Data Index: 5690612 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6481. Min Range: -6.6481
Max Act: 6.1793. Min Act: -0.1700
Data Index: 888517 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6481. Min Range: -6.6481
Max Act: 6.1793. Min Act: -0.1700
Data Index: 2963837 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6481. Min Range: -6.6481
Max Act: 6.1793. Min Act: -0.1700
Data Index: 7962839 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6481. Min Range: -6.6481
Max Act: 6.1793. Min Act: -0.1700
Data Index: 7653084 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6481. Min Range: -6.6481
Max Act: 6.1481. Min Act: -0.1700
Data Index: 7818692 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6481. Min Range: -6.6481
Max Act: 6.1168. Min Act: -0.1700
Data Index: 676493 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6481. Min Range: -6.6481
Max Act: 6.1481. Min Act: -0.1700
Data Index: 8356553 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6481. Min Range: -6.6481
Max Act: 6.1168. Min Act: -0.1700
Data Index: 1608225 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6481. Min Range: -6.6481
Max Act: 6.1168. Min Act: -0.1700
Data Index: 2779913 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6481. Min Range: -6.6481
Max Act: 6.1168. Min Act: -0.1700
Data Index: 2195971 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19