Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5240 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2041. Min Range: -5.2041
Max Act: 5.2041. Min Act: -0.1700
Data Index: 5400809 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2041. Min Range: -5.2041
Max Act: 5.2041. Min Act: -0.1700
Data Index: 7294166 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2041. Min Range: -5.2041
Max Act: 5.1729. Min Act: -0.1700
Data Index: 8325531 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2041. Min Range: -5.2041
Max Act: 5.1729. Min Act: -0.1700
Data Index: 2875473 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2041. Min Range: -5.2041
Max Act: 5.1104. Min Act: -0.1700
Data Index: 5878016 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2041. Min Range: -5.2041
Max Act: 5.1104. Min Act: -0.1700
Data Index: 6399554 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2041. Min Range: -5.2041
Max Act: 5.0791. Min Act: -0.1700
Data Index: 8595588 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2041. Min Range: -5.2041
Max Act: 5.0791. Min Act: -0.1700
Data Index: 3597915 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2041. Min Range: -5.2041
Max Act: 5.0479. Min Act: -0.1700
Data Index: 6588549 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2041. Min Range: -5.2041
Max Act: 5.0166. Min Act: -0.1700
Data Index: 7123395 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2041. Min Range: -5.2041
Max Act: 5.0166. Min Act: -0.1700
Data Index: 2659540 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2041. Min Range: -5.2041
Max Act: 5.0166. Min Act: -0.1700
Data Index: 5604999 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2041. Min Range: -5.2041
Max Act: 4.9854. Min Act: -0.1700
Data Index: 3981707 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2041. Min Range: -5.2041
Max Act: 4.9854. Min Act: -0.1700
Data Index: 705849 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2041. Min Range: -5.2041
Max Act: 4.9854. Min Act: -0.1700
Data Index: 382615 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2041. Min Range: -5.2041
Max Act: 4.9854. Min Act: -0.1700
Data Index: 8328441 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2041. Min Range: -5.2041
Max Act: 4.9854. Min Act: -0.1700
Data Index: 3860853 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2041. Min Range: -5.2041
Max Act: 4.9854. Min Act: -0.1700
Data Index: 5586049 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2041. Min Range: -5.2041
Max Act: 4.9541. Min Act: -0.1700
Data Index: 5519677 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2041. Min Range: -5.2041
Max Act: 4.9229. Min Act: -0.1700
Data Index: 708908 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19