Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1729 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2932. Min Range: -3.2932
Max Act: 3.2932. Min Act: -0.1700
Data Index: 52291 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2932. Min Range: -3.2932
Max Act: 3.2461. Min Act: -0.1700
Data Index: 1173098 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2932. Min Range: -3.2932
Max Act: 3.2461. Min Act: -0.1700
Data Index: 4755479 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2932. Min Range: -3.2932
Max Act: 3.1832. Min Act: -0.1700
Data Index: 6043561 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2932. Min Range: -3.2932
Max Act: 3.1832. Min Act: -0.1700
Data Index: 161898 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2932. Min Range: -3.2932
Max Act: 3.1675. Min Act: -0.1700
Data Index: 319069 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2932. Min Range: -3.2932
Max Act: 3.1360. Min Act: -0.1700
Data Index: 3632227 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2932. Min Range: -3.2932
Max Act: 3.1360. Min Act: -0.1700
Data Index: 3894795 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2932. Min Range: -3.2932
Max Act: 3.1517. Min Act: -0.1700
Data Index: 6695478 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2932. Min Range: -3.2932
Max Act: 3.1202. Min Act: -0.1700
Data Index: 8591445 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2932. Min Range: -3.2932
Max Act: 3.1202. Min Act: -0.1700
Data Index: 7492270 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2932. Min Range: -3.2932
Max Act: 3.0887. Min Act: -0.1700
Data Index: 1173100 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2932. Min Range: -3.2932
Max Act: 3.0256. Min Act: -0.1700
Data Index: 1519229 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2932. Min Range: -3.2932
Max Act: 3.0098. Min Act: -0.1700
Data Index: 270872 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2932. Min Range: -3.2932
Max Act: 3.0256. Min Act: -0.1700
Data Index: 1173103 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2932. Min Range: -3.2932
Max Act: 3.0256. Min Act: -0.1700
Data Index: 1173102 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2932. Min Range: -3.2932
Max Act: 3.0256. Min Act: -0.1700
Data Index: 7563516 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2932. Min Range: -3.2932
Max Act: 2.9940. Min Act: -0.1700
Data Index: 7115774 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2932. Min Range: -3.2932
Max Act: 2.9782. Min Act: -0.1700
Data Index: 3614642 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2932. Min Range: -3.2932
Max Act: 2.9624. Min Act: -0.1700
Data Index: 2977999 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19