Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1923 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.7462. Min Range: -8.7462
Max Act: 8.7462. Min Act: -0.1700
Data Index: 1720722 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7462. Min Range: -8.7462
Max Act: 8.7462. Min Act: -0.1700
Data Index: 5869572 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7462. Min Range: -8.7462
Max Act: 8.6212. Min Act: -0.1700
Data Index: 206836 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7462. Min Range: -8.7462
Max Act: 8.6212. Min Act: -0.1700
Data Index: 1248105 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7462. Min Range: -8.7462
Max Act: 8.5587. Min Act: -0.1700
Data Index: 3640875 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7462. Min Range: -8.7462
Max Act: 8.5587. Min Act: -0.1700
Data Index: 3316992 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7462. Min Range: -8.7462
Max Act: 8.5587. Min Act: -0.1700
Data Index: 1244339 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7462. Min Range: -8.7462
Max Act: 8.5587. Min Act: -0.1700
Data Index: 8132698 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7462. Min Range: -8.7462
Max Act: 8.5587. Min Act: -0.1700
Data Index: 7401160 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7462. Min Range: -8.7462
Max Act: 8.5587. Min Act: -0.1700
Data Index: 5221728 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7462. Min Range: -8.7462
Max Act: 8.4962. Min Act: -0.1700
Data Index: 3325240 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7462. Min Range: -8.7462
Max Act: 8.4962. Min Act: -0.1700
Data Index: 8384819 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7462. Min Range: -8.7462
Max Act: 8.4962. Min Act: -0.1700
Data Index: 6451650 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7462. Min Range: -8.7462
Max Act: 8.4962. Min Act: -0.1700
Data Index: 1424211 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7462. Min Range: -8.7462
Max Act: 8.4962. Min Act: -0.1700
Data Index: 6631339 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7462. Min Range: -8.7462
Max Act: 8.4337. Min Act: -0.1700
Data Index: 8040213 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7462. Min Range: -8.7462
Max Act: 8.4337. Min Act: -0.1700
Data Index: 4410590 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7462. Min Range: -8.7462
Max Act: 8.4337. Min Act: -0.1700
Data Index: 8204083 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7462. Min Range: -8.7462
Max Act: 8.4337. Min Act: -0.1700
Data Index: 1244322 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7462. Min Range: -8.7462
Max Act: 8.3712. Min Act: -0.1700
Data Index: 689398 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19