Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3223 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4296. Min Range: -5.4296
Max Act: 5.4296. Min Act: -0.1700
Data Index: 4374167 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4296. Min Range: -5.4296
Max Act: 5.4296. Min Act: -0.1700
Data Index: 4736410 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4296. Min Range: -5.4296
Max Act: 5.3671. Min Act: -0.1700
Data Index: 7039678 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4296. Min Range: -5.4296
Max Act: 5.3359. Min Act: -0.1700
Data Index: 6773844 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4296. Min Range: -5.4296
Max Act: 5.3046. Min Act: -0.1700
Data Index: 8347437 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4296. Min Range: -5.4296
Max Act: 5.2421. Min Act: -0.1700
Data Index: 7940357 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4296. Min Range: -5.4296
Max Act: 5.1796. Min Act: -0.1700
Data Index: 5357936 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4296. Min Range: -5.4296
Max Act: 5.1796. Min Act: -0.1700
Data Index: 538982 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4296. Min Range: -5.4296
Max Act: 5.2109. Min Act: -0.1700
Data Index: 290361 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4296. Min Range: -5.4296
Max Act: 5.1796. Min Act: -0.1700
Data Index: 1645484 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4296. Min Range: -5.4296
Max Act: 5.1484. Min Act: -0.1700
Data Index: 4444577 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4296. Min Range: -5.4296
Max Act: 5.1171. Min Act: -0.1700
Data Index: 4446417 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4296. Min Range: -5.4296
Max Act: 5.1171. Min Act: -0.1700
Data Index: 5712195 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4296. Min Range: -5.4296
Max Act: 5.0859. Min Act: -0.1700
Data Index: 4538719 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4296. Min Range: -5.4296
Max Act: 5.1171. Min Act: -0.1700
Data Index: 2132061 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4296. Min Range: -5.4296
Max Act: 5.0859. Min Act: -0.1700
Data Index: 3929452 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4296. Min Range: -5.4296
Max Act: 5.0859. Min Act: -0.1700
Data Index: 996467 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4296. Min Range: -5.4296
Max Act: 5.0859. Min Act: -0.1700
Data Index: 7809214 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4296. Min Range: -5.4296
Max Act: 5.0859. Min Act: -0.1700
Data Index: 900058 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4296. Min Range: -5.4296
Max Act: 5.0546. Min Act: -0.1700
Data Index: 1076296 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19