Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4796 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6381. Min Range: -5.6381
Max Act: 5.6381. Min Act: -0.1700
Data Index: 4103764 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6381. Min Range: -5.6381
Max Act: 5.6069. Min Act: -0.1700
Data Index: 2291424 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6381. Min Range: -5.6381
Max Act: 5.5756. Min Act: -0.1700
Data Index: 3476988 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6381. Min Range: -5.6381
Max Act: 5.5756. Min Act: -0.1700
Data Index: 1635697 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6381. Min Range: -5.6381
Max Act: 5.5756. Min Act: -0.1700
Data Index: 1457518 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6381. Min Range: -5.6381
Max Act: 5.4819. Min Act: -0.1700
Data Index: 8478339 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6381. Min Range: -5.6381
Max Act: 5.5131. Min Act: -0.1700
Data Index: 6871784 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6381. Min Range: -5.6381
Max Act: 5.4819. Min Act: -0.1700
Data Index: 3236990 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6381. Min Range: -5.6381
Max Act: 5.4819. Min Act: -0.1700
Data Index: 5359934 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6381. Min Range: -5.6381
Max Act: 5.4819. Min Act: -0.1700
Data Index: 3236721 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6381. Min Range: -5.6381
Max Act: 5.4506. Min Act: -0.1700
Data Index: 6933105 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6381. Min Range: -5.6381
Max Act: 5.4506. Min Act: -0.1700
Data Index: 1469715 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6381. Min Range: -5.6381
Max Act: 5.4506. Min Act: -0.1700
Data Index: 1931653 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6381. Min Range: -5.6381
Max Act: 5.4506. Min Act: -0.1700
Data Index: 8153607 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6381. Min Range: -5.6381
Max Act: 5.4194. Min Act: -0.1700
Data Index: 428887 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6381. Min Range: -5.6381
Max Act: 5.3569. Min Act: -0.1700
Data Index: 4408880 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6381. Min Range: -5.6381
Max Act: 5.3881. Min Act: -0.1700
Data Index: 3061455 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6381. Min Range: -5.6381
Max Act: 5.3569. Min Act: -0.1700
Data Index: 2001595 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6381. Min Range: -5.6381
Max Act: 5.3881. Min Act: -0.1700
Data Index: 952299 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6381. Min Range: -5.6381
Max Act: 5.3881. Min Act: -0.1700
Data Index: 3562498 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19