Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5323 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0405. Min Range: -5.0405
Max Act: 5.0405. Min Act: -0.1700
Data Index: 1210395 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0405. Min Range: -5.0405
Max Act: 5.0405. Min Act: -0.1700
Data Index: 2423710 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0405. Min Range: -5.0405
Max Act: 5.0405. Min Act: -0.1700
Data Index: 2697093 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0405. Min Range: -5.0405
Max Act: 5.0092. Min Act: -0.1700
Data Index: 8397225 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0405. Min Range: -5.0405
Max Act: 4.9780. Min Act: -0.1700
Data Index: 4331755 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0405. Min Range: -5.0405
Max Act: 4.9467. Min Act: -0.1700
Data Index: 4957300 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0405. Min Range: -5.0405
Max Act: 4.9155. Min Act: -0.1700
Data Index: 8220424 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0405. Min Range: -5.0405
Max Act: 4.9155. Min Act: -0.1700
Data Index: 495902 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0405. Min Range: -5.0405
Max Act: 4.8842. Min Act: -0.1700
Data Index: 6456362 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0405. Min Range: -5.0405
Max Act: 4.8842. Min Act: -0.1700
Data Index: 2705682 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0405. Min Range: -5.0405
Max Act: 4.8842. Min Act: -0.1700
Data Index: 1390190 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0405. Min Range: -5.0405
Max Act: 4.8842. Min Act: -0.1700
Data Index: 1358375 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0405. Min Range: -5.0405
Max Act: 4.8842. Min Act: -0.1700
Data Index: 311634 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0405. Min Range: -5.0405
Max Act: 4.8842. Min Act: -0.1700
Data Index: 4443992 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0405. Min Range: -5.0405
Max Act: 4.8842. Min Act: -0.1700
Data Index: 7360656 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0405. Min Range: -5.0405
Max Act: 4.8530. Min Act: -0.1700
Data Index: 1421835 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0405. Min Range: -5.0405
Max Act: 4.8217. Min Act: -0.1700
Data Index: 432667 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0405. Min Range: -5.0405
Max Act: 4.8217. Min Act: -0.1700
Data Index: 2637482 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0405. Min Range: -5.0405
Max Act: 4.8530. Min Act: -0.1700
Data Index: 6192567 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0405. Min Range: -5.0405
Max Act: 4.8530. Min Act: -0.1700
Data Index: 4408677 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19