Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3659 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6631. Min Range: -2.6631
Max Act: 2.6631. Min Act: -0.1700
Data Index: 6904288 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6631. Min Range: -2.6631
Max Act: 2.6471. Min Act: -0.1700
Data Index: 2309491 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6631. Min Range: -2.6631
Max Act: 2.6471. Min Act: -0.1700
Data Index: 8020467 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6631. Min Range: -2.6631
Max Act: 2.6631. Min Act: -0.1700
Data Index: 5684307 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6631. Min Range: -2.6631
Max Act: 2.6471. Min Act: -0.1700
Data Index: 6598227 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6631. Min Range: -2.6631
Max Act: 2.6310. Min Act: -0.1700
Data Index: 4397808 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6631. Min Range: -2.6631
Max Act: 2.6149. Min Act: -0.1700
Data Index: 2417504 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6631. Min Range: -2.6631
Max Act: 2.6149. Min Act: -0.1700
Data Index: 5271088 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6631. Min Range: -2.6631
Max Act: 2.6149. Min Act: -0.1700
Data Index: 323286 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6631. Min Range: -2.6631
Max Act: 2.6149. Min Act: -0.1700
Data Index: 6048821 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6631. Min Range: -2.6631
Max Act: 2.5988. Min Act: -0.1700
Data Index: 7869159 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6631. Min Range: -2.6631
Max Act: 2.5827. Min Act: -0.1700
Data Index: 1792287 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6631. Min Range: -2.6631
Max Act: 2.5827. Min Act: -0.1700
Data Index: 3957597 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6631. Min Range: -2.6631
Max Act: 2.5988. Min Act: -0.1700
Data Index: 8310945 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6631. Min Range: -2.6631
Max Act: 2.5827. Min Act: -0.1700
Data Index: 1191951 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6631. Min Range: -2.6631
Max Act: 2.5827. Min Act: -0.1700
Data Index: 6898303 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6631. Min Range: -2.6631
Max Act: 2.5827. Min Act: -0.1700
Data Index: 5404623 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6631. Min Range: -2.6631
Max Act: 2.5827. Min Act: -0.1700
Data Index: 2743784 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6631. Min Range: -2.6631
Max Act: 2.5505. Min Act: -0.1700
Data Index: 379552 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6631. Min Range: -2.6631
Max Act: 2.5666. Min Act: -0.1700
Data Index: 1366391 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19