Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 531 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7041. Min Range: -4.7041
Max Act: 4.7041. Min Act: -0.1700
Data Index: 6221052 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7041. Min Range: -4.7041
Max Act: 4.5791. Min Act: -0.1700
Data Index: 840627 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7041. Min Range: -4.7041
Max Act: 4.5791. Min Act: -0.1700
Data Index: 4003349 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7041. Min Range: -4.7041
Max Act: 4.5166. Min Act: -0.1700
Data Index: 6468958 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7041. Min Range: -4.7041
Max Act: 4.5166. Min Act: -0.1700
Data Index: 2879573 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7041. Min Range: -4.7041
Max Act: 4.4541. Min Act: -0.1700
Data Index: 6928466 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7041. Min Range: -4.7041
Max Act: 4.4541. Min Act: -0.1700
Data Index: 7567969 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7041. Min Range: -4.7041
Max Act: 4.4541. Min Act: -0.1700
Data Index: 3380815 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7041. Min Range: -4.7041
Max Act: 4.4229. Min Act: -0.1700
Data Index: 2418429 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7041. Min Range: -4.7041
Max Act: 4.4229. Min Act: -0.1700
Data Index: 112204 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7041. Min Range: -4.7041
Max Act: 4.3916. Min Act: -0.1700
Data Index: 1485884 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7041. Min Range: -4.7041
Max Act: 4.3604. Min Act: -0.1700
Data Index: 1009130 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7041. Min Range: -4.7041
Max Act: 4.3604. Min Act: -0.1700
Data Index: 2687765 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7041. Min Range: -4.7041
Max Act: 4.3604. Min Act: -0.1700
Data Index: 575079 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7041. Min Range: -4.7041
Max Act: 4.3604. Min Act: -0.1700
Data Index: 4605674 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7041. Min Range: -4.7041
Max Act: 4.3604. Min Act: -0.1700
Data Index: 4173487 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7041. Min Range: -4.7041
Max Act: 4.3604. Min Act: -0.1700
Data Index: 6714970 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7041. Min Range: -4.7041
Max Act: 4.3916. Min Act: -0.1700
Data Index: 3154626 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7041. Min Range: -4.7041
Max Act: 4.3291. Min Act: -0.1700
Data Index: 1178002 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7041. Min Range: -4.7041
Max Act: 4.3291. Min Act: -0.1700
Data Index: 3681285 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19