Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 932 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1500. Min Range: -5.1500
Max Act: 5.1500. Min Act: -0.1700
Data Index: 1168464 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1500. Min Range: -5.1500
Max Act: 5.0562. Min Act: -0.1700
Data Index: 1003236 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1500. Min Range: -5.1500
Max Act: 4.8687. Min Act: -0.1700
Data Index: 6961989 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1500. Min Range: -5.1500
Max Act: 4.9000. Min Act: -0.1700
Data Index: 5809919 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1500. Min Range: -5.1500
Max Act: 4.9000. Min Act: -0.1700
Data Index: 623209 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1500. Min Range: -5.1500
Max Act: 4.8687. Min Act: -0.1700
Data Index: 3641065 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1500. Min Range: -5.1500
Max Act: 4.8687. Min Act: -0.1700
Data Index: 5235600 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1500. Min Range: -5.1500
Max Act: 4.8687. Min Act: -0.1700
Data Index: 402068 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1500. Min Range: -5.1500
Max Act: 4.8687. Min Act: -0.1700
Data Index: 8678677 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1500. Min Range: -5.1500
Max Act: 4.8687. Min Act: -0.1700
Data Index: 6290590 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1500. Min Range: -5.1500
Max Act: 4.8375. Min Act: -0.1700
Data Index: 6479072 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1500. Min Range: -5.1500
Max Act: 4.8375. Min Act: -0.1700
Data Index: 5235601 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1500. Min Range: -5.1500
Max Act: 4.8687. Min Act: -0.1700
Data Index: 3731718 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1500. Min Range: -5.1500
Max Act: 4.8375. Min Act: -0.1700
Data Index: 1453244 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1500. Min Range: -5.1500
Max Act: 4.8062. Min Act: -0.1700
Data Index: 611472 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1500. Min Range: -5.1500
Max Act: 4.8062. Min Act: -0.1700
Data Index: 603650 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1500. Min Range: -5.1500
Max Act: 4.8062. Min Act: -0.1700
Data Index: 7570001 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1500. Min Range: -5.1500
Max Act: 4.7750. Min Act: -0.1700
Data Index: 2816802 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1500. Min Range: -5.1500
Max Act: 4.7437. Min Act: -0.1700
Data Index: 5659282 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1500. Min Range: -5.1500
Max Act: 4.7437. Min Act: -0.1700
Data Index: 7204727 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19