Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 518 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.7041. Min Range: -9.7041
Max Act: 9.7041. Min Act: -0.1700
Data Index: 4319179 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7041. Min Range: -9.7041
Max Act: 9.5166. Min Act: -0.1700
Data Index: 4869495 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7041. Min Range: -9.7041
Max Act: 9.4541. Min Act: -0.1700
Data Index: 2083499 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7041. Min Range: -9.7041
Max Act: 9.3916. Min Act: -0.1700
Data Index: 726525 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7041. Min Range: -9.7041
Max Act: 9.3291. Min Act: -0.1700
Data Index: 1144490 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7041. Min Range: -9.7041
Max Act: 9.3291. Min Act: -0.1700
Data Index: 2766014 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7041. Min Range: -9.7041
Max Act: 9.2666. Min Act: -0.1700
Data Index: 8117229 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7041. Min Range: -9.7041
Max Act: 9.2666. Min Act: -0.1700
Data Index: 1809302 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7041. Min Range: -9.7041
Max Act: 9.2666. Min Act: -0.1700
Data Index: 7381569 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7041. Min Range: -9.7041
Max Act: 9.2041. Min Act: -0.1700
Data Index: 1233739 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7041. Min Range: -9.7041
Max Act: 9.2041. Min Act: -0.1700
Data Index: 483584 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7041. Min Range: -9.7041
Max Act: 9.1416. Min Act: -0.1700
Data Index: 4307584 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7041. Min Range: -9.7041
Max Act: 9.1416. Min Act: -0.1700
Data Index: 1500018 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7041. Min Range: -9.7041
Max Act: 9.1416. Min Act: -0.1700
Data Index: 7917997 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7041. Min Range: -9.7041
Max Act: 9.0791. Min Act: -0.1700
Data Index: 7321368 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7041. Min Range: -9.7041
Max Act: 9.0791. Min Act: -0.1700
Data Index: 2790488 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7041. Min Range: -9.7041
Max Act: 9.1416. Min Act: -0.1700
Data Index: 4315933 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7041. Min Range: -9.7041
Max Act: 9.1416. Min Act: -0.1700
Data Index: 7112830 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7041. Min Range: -9.7041
Max Act: 9.0791. Min Act: -0.1700
Data Index: 106586 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7041. Min Range: -9.7041
Max Act: 9.0791. Min Act: -0.1700
Data Index: 2813665 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19