Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2649 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2929. Min Range: -5.2929
Max Act: 5.2929. Min Act: -0.1700
Data Index: 7774265 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2929. Min Range: -5.2929
Max Act: 5.2929. Min Act: -0.1700
Data Index: 3563470 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2929. Min Range: -5.2929
Max Act: 5.2616. Min Act: -0.1700
Data Index: 5879385 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2929. Min Range: -5.2929
Max Act: 5.2304. Min Act: -0.1700
Data Index: 8470318 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2929. Min Range: -5.2929
Max Act: 5.1054. Min Act: -0.1700
Data Index: 8222000 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2929. Min Range: -5.2929
Max Act: 5.0741. Min Act: -0.1700
Data Index: 3393400 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2929. Min Range: -5.2929
Max Act: 5.0429. Min Act: -0.1700
Data Index: 3369878 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2929. Min Range: -5.2929
Max Act: 5.0116. Min Act: -0.1700
Data Index: 1284505 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2929. Min Range: -5.2929
Max Act: 5.0116. Min Act: -0.1700
Data Index: 6194335 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2929. Min Range: -5.2929
Max Act: 5.0116. Min Act: -0.1700
Data Index: 6513488 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2929. Min Range: -5.2929
Max Act: 4.9179. Min Act: -0.1700
Data Index: 1725945 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2929. Min Range: -5.2929
Max Act: 4.9491. Min Act: -0.1700
Data Index: 4025281 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2929. Min Range: -5.2929
Max Act: 4.9491. Min Act: -0.1700
Data Index: 8774696 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2929. Min Range: -5.2929
Max Act: 4.9491. Min Act: -0.1700
Data Index: 2310859 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2929. Min Range: -5.2929
Max Act: 4.9179. Min Act: -0.1700
Data Index: 5002117 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2929. Min Range: -5.2929
Max Act: 4.9179. Min Act: -0.1700
Data Index: 3650014 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2929. Min Range: -5.2929
Max Act: 4.9179. Min Act: -0.1700
Data Index: 7705747 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2929. Min Range: -5.2929
Max Act: 4.8554. Min Act: -0.1700
Data Index: 5228378 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2929. Min Range: -5.2929
Max Act: 4.8866. Min Act: -0.1700
Data Index: 6958337 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2929. Min Range: -5.2929
Max Act: 4.8866. Min Act: -0.1700
Data Index: 4202769 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19