Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3580 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9270. Min Range: -2.9270
Max Act: 2.9270. Min Act: -0.1700
Data Index: 6233867 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9270. Min Range: -2.9270
Max Act: 2.8317. Min Act: -0.1700
Data Index: 1430712 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9270. Min Range: -2.9270
Max Act: 2.7999. Min Act: -0.1700
Data Index: 1787369 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9270. Min Range: -2.9270
Max Act: 2.7361. Min Act: -0.1700
Data Index: 7399928 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9270. Min Range: -2.9270
Max Act: 2.7201. Min Act: -0.1700
Data Index: 4917889 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9270. Min Range: -2.9270
Max Act: 2.7041. Min Act: -0.1700
Data Index: 2340667 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9270. Min Range: -2.9270
Max Act: 2.7201. Min Act: -0.1700
Data Index: 3079928 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9270. Min Range: -2.9270
Max Act: 2.7361. Min Act: -0.1700
Data Index: 355682 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9270. Min Range: -2.9270
Max Act: 2.6881. Min Act: -0.1700
Data Index: 5742622 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9270. Min Range: -2.9270
Max Act: 2.7201. Min Act: -0.1700
Data Index: 8223675 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9270. Min Range: -2.9270
Max Act: 2.7041. Min Act: -0.1700
Data Index: 3142358 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9270. Min Range: -2.9270
Max Act: 2.7041. Min Act: -0.1700
Data Index: 8644004 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9270. Min Range: -2.9270
Max Act: 2.6881. Min Act: -0.1700
Data Index: 3295121 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9270. Min Range: -2.9270
Max Act: 2.6881. Min Act: -0.1700
Data Index: 3733107 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9270. Min Range: -2.9270
Max Act: 2.6881. Min Act: -0.1700
Data Index: 3208808 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9270. Min Range: -2.9270
Max Act: 2.6561. Min Act: -0.1700
Data Index: 8345467 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9270. Min Range: -2.9270
Max Act: 2.6881. Min Act: -0.1700
Data Index: 547452 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9270. Min Range: -2.9270
Max Act: 2.6721. Min Act: -0.1700
Data Index: 448722 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9270. Min Range: -2.9270
Max Act: 2.6561. Min Act: -0.1700
Data Index: 3580598 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9270. Min Range: -2.9270
Max Act: 2.6400. Min Act: -0.1700
Data Index: 8186734 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19