Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1230 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4228. Min Range: -6.4228
Max Act: 6.4228. Min Act: -0.1700
Data Index: 515076 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4228. Min Range: -6.4228
Max Act: 6.4228. Min Act: -0.1700
Data Index: 2579112 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4228. Min Range: -6.4228
Max Act: 6.3916. Min Act: -0.1700
Data Index: 2579108 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4228. Min Range: -6.4228
Max Act: 6.3603. Min Act: -0.1700
Data Index: 4346507 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4228. Min Range: -6.4228
Max Act: 6.2978. Min Act: -0.1700
Data Index: 6512045 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4228. Min Range: -6.4228
Max Act: 6.2978. Min Act: -0.1700
Data Index: 7385860 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4228. Min Range: -6.4228
Max Act: 6.2666. Min Act: -0.1700
Data Index: 1442473 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4228. Min Range: -6.4228
Max Act: 6.2041. Min Act: -0.1700
Data Index: 6704186 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4228. Min Range: -6.4228
Max Act: 6.1728. Min Act: -0.1700
Data Index: 7186707 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4228. Min Range: -6.4228
Max Act: 6.2041. Min Act: -0.1700
Data Index: 8173282 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4228. Min Range: -6.4228
Max Act: 6.2041. Min Act: -0.1700
Data Index: 4120951 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4228. Min Range: -6.4228
Max Act: 6.1728. Min Act: -0.1700
Data Index: 8594340 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4228. Min Range: -6.4228
Max Act: 6.1416. Min Act: -0.1700
Data Index: 2865899 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4228. Min Range: -6.4228
Max Act: 6.1416. Min Act: -0.1700
Data Index: 4462392 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4228. Min Range: -6.4228
Max Act: 6.0478. Min Act: -0.1700
Data Index: 6563550 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4228. Min Range: -6.4228
Max Act: 6.0791. Min Act: -0.1700
Data Index: 3789511 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4228. Min Range: -6.4228
Max Act: 6.1103. Min Act: -0.1700
Data Index: 4419646 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4228. Min Range: -6.4228
Max Act: 6.1103. Min Act: -0.1700
Data Index: 8411056 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4228. Min Range: -6.4228
Max Act: 6.0791. Min Act: -0.1700
Data Index: 502852 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4228. Min Range: -6.4228
Max Act: 6.0791. Min Act: -0.1700
Data Index: 6579850 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19