Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3343 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1068. Min Range: -5.1068
Max Act: 5.1068. Min Act: -0.1700
Data Index: 7150282 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1068. Min Range: -5.1068
Max Act: 5.0756. Min Act: -0.1700
Data Index: 5458786 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1068. Min Range: -5.1068
Max Act: 4.9818. Min Act: -0.1700
Data Index: 8532233 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1068. Min Range: -5.1068
Max Act: 4.8568. Min Act: -0.1700
Data Index: 6925614 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1068. Min Range: -5.1068
Max Act: 4.8256. Min Act: -0.1700
Data Index: 1719242 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1068. Min Range: -5.1068
Max Act: 4.8256. Min Act: -0.1700
Data Index: 5458796 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1068. Min Range: -5.1068
Max Act: 4.7943. Min Act: -0.1700
Data Index: 5532461 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1068. Min Range: -5.1068
Max Act: 4.7943. Min Act: -0.1700
Data Index: 1090091 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1068. Min Range: -5.1068
Max Act: 4.7631. Min Act: -0.1700
Data Index: 3224691 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1068. Min Range: -5.1068
Max Act: 4.7318. Min Act: -0.1700
Data Index: 517598 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1068. Min Range: -5.1068
Max Act: 4.7318. Min Act: -0.1700
Data Index: 2428102 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1068. Min Range: -5.1068
Max Act: 4.7006. Min Act: -0.1700
Data Index: 8691576 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1068. Min Range: -5.1068
Max Act: 4.7006. Min Act: -0.1700
Data Index: 5124872 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1068. Min Range: -5.1068
Max Act: 4.7006. Min Act: -0.1700
Data Index: 7836686 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1068. Min Range: -5.1068
Max Act: 4.7006. Min Act: -0.1700
Data Index: 2966335 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1068. Min Range: -5.1068
Max Act: 4.6693. Min Act: -0.1700
Data Index: 1563757 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1068. Min Range: -5.1068
Max Act: 4.6693. Min Act: -0.1700
Data Index: 5760399 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1068. Min Range: -5.1068
Max Act: 4.6693. Min Act: -0.1700
Data Index: 6559077 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1068. Min Range: -5.1068
Max Act: 4.6693. Min Act: -0.1700
Data Index: 2410281 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1068. Min Range: -5.1068
Max Act: 4.6693. Min Act: -0.1700
Data Index: 4592344 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19