Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 193 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.5340. Min Act: -0.1700
Data Index: 4860238 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.4402. Min Act: -0.1700
Data Index: 3040833 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.3465. Min Act: -0.1700
Data Index: 5668844 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.3465. Min Act: -0.1700
Data Index: 2528551 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.2840. Min Act: -0.1700
Data Index: 369621 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.2840. Min Act: -0.1700
Data Index: 7480859 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.2840. Min Act: -0.1700
Data Index: 2527703 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.2840. Min Act: -0.1700
Data Index: 6445909 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.2527. Min Act: -0.1700
Data Index: 8695500 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.2215. Min Act: -0.1700
Data Index: 3499329 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.2215. Min Act: -0.1700
Data Index: 224319 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.2215. Min Act: -0.1700
Data Index: 7433825 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.1902. Min Act: -0.1700
Data Index: 1437620 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.1902. Min Act: -0.1700
Data Index: 6759695 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.1590. Min Act: -0.1700
Data Index: 5557809 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.1590. Min Act: -0.1700
Data Index: 6321381 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.1590. Min Act: -0.1700
Data Index: 3372729 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.1590. Min Act: -0.1700
Data Index: 8299357 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.1590. Min Act: -0.1700
Data Index: 3372027 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.1590. Min Act: -0.1700
Data Index: 2872538 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19