Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 976 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2514. Min Range: -3.2514
Max Act: 3.2514. Min Act: -0.1700
Data Index: 8266818 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2514. Min Range: -3.2514
Max Act: 3.2514. Min Act: -0.1700
Data Index: 8266828 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2514. Min Range: -3.2514
Max Act: 3.2199. Min Act: -0.1700
Data Index: 7836709 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2514. Min Range: -3.2514
Max Act: 3.1727. Min Act: -0.1700
Data Index: 3396965 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2514. Min Range: -3.2514
Max Act: 3.1885. Min Act: -0.1700
Data Index: 1223712 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2514. Min Range: -3.2514
Max Act: 3.1727. Min Act: -0.1700
Data Index: 6533114 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2514. Min Range: -3.2514
Max Act: 3.1727. Min Act: -0.1700
Data Index: 1565585 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2514. Min Range: -3.2514
Max Act: 3.1885. Min Act: -0.1700
Data Index: 4054413 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2514. Min Range: -3.2514
Max Act: 3.1413. Min Act: -0.1700
Data Index: 4184449 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2514. Min Range: -3.2514
Max Act: 3.1098. Min Act: -0.1700
Data Index: 3481823 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2514. Min Range: -3.2514
Max Act: 3.1255. Min Act: -0.1700
Data Index: 3622699 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2514. Min Range: -3.2514
Max Act: 3.1255. Min Act: -0.1700
Data Index: 4457282 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2514. Min Range: -3.2514
Max Act: 3.0782. Min Act: -0.1700
Data Index: 714324 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2514. Min Range: -3.2514
Max Act: 3.0467. Min Act: -0.1700
Data Index: 5463777 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2514. Min Range: -3.2514
Max Act: 3.0625. Min Act: -0.1700
Data Index: 4347385 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2514. Min Range: -3.2514
Max Act: 3.0309. Min Act: -0.1700
Data Index: 181503 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2514. Min Range: -3.2514
Max Act: 3.0625. Min Act: -0.1700
Data Index: 5309083 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2514. Min Range: -3.2514
Max Act: 3.0625. Min Act: -0.1700
Data Index: 269805 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2514. Min Range: -3.2514
Max Act: 3.0151. Min Act: -0.1700
Data Index: 1642054 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2514. Min Range: -3.2514
Max Act: 3.0467. Min Act: -0.1700
Data Index: 2074673 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19