Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 219 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3270. Min Range: -6.3270
Max Act: 6.3270. Min Act: -0.1700
Data Index: 5641847 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3270. Min Range: -6.3270
Max Act: 6.2020. Min Act: -0.1700
Data Index: 7685290 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3270. Min Range: -6.3270
Max Act: 6.0145. Min Act: -0.1700
Data Index: 3340676 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3270. Min Range: -6.3270
Max Act: 6.0145. Min Act: -0.1700
Data Index: 5267141 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3270. Min Range: -6.3270
Max Act: 5.9520. Min Act: -0.1700
Data Index: 4530221 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3270. Min Range: -6.3270
Max Act: 5.9520. Min Act: -0.1700
Data Index: 4300127 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3270. Min Range: -6.3270
Max Act: 5.8895. Min Act: -0.1700
Data Index: 4320783 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3270. Min Range: -6.3270
Max Act: 5.8582. Min Act: -0.1700
Data Index: 3750496 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3270. Min Range: -6.3270
Max Act: 5.9207. Min Act: -0.1700
Data Index: 1282932 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3270. Min Range: -6.3270
Max Act: 5.8582. Min Act: -0.1700
Data Index: 3475443 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3270. Min Range: -6.3270
Max Act: 5.8582. Min Act: -0.1700
Data Index: 5999263 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3270. Min Range: -6.3270
Max Act: 5.8582. Min Act: -0.1700
Data Index: 3661755 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3270. Min Range: -6.3270
Max Act: 5.8270. Min Act: -0.1700
Data Index: 7366330 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3270. Min Range: -6.3270
Max Act: 5.7957. Min Act: -0.1700
Data Index: 154708 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3270. Min Range: -6.3270
Max Act: 5.7957. Min Act: -0.1700
Data Index: 700510 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3270. Min Range: -6.3270
Max Act: 5.7645. Min Act: -0.1700
Data Index: 400258 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3270. Min Range: -6.3270
Max Act: 5.7957. Min Act: -0.1700
Data Index: 6935194 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3270. Min Range: -6.3270
Max Act: 5.7957. Min Act: -0.1700
Data Index: 7474215 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3270. Min Range: -6.3270
Max Act: 5.7645. Min Act: -0.1700
Data Index: 1510091 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3270. Min Range: -6.3270
Max Act: 5.7332. Min Act: -0.1700
Data Index: 7155071 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19