Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4590 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5015. Min Range: -6.5015
Max Act: 6.5015. Min Act: -0.1700
Data Index: 551111 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5015. Min Range: -6.5015
Max Act: 6.5015. Min Act: -0.1700
Data Index: 2426408 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5015. Min Range: -6.5015
Max Act: 6.4702. Min Act: -0.1700
Data Index: 2962343 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5015. Min Range: -6.5015
Max Act: 6.3765. Min Act: -0.1700
Data Index: 1380492 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5015. Min Range: -6.5015
Max Act: 6.4077. Min Act: -0.1700
Data Index: 6346858 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5015. Min Range: -6.5015
Max Act: 6.3765. Min Act: -0.1700
Data Index: 5705387 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5015. Min Range: -6.5015
Max Act: 6.3765. Min Act: -0.1700
Data Index: 5829035 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5015. Min Range: -6.5015
Max Act: 6.3765. Min Act: -0.1700
Data Index: 8426786 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5015. Min Range: -6.5015
Max Act: 6.3765. Min Act: -0.1700
Data Index: 3485514 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5015. Min Range: -6.5015
Max Act: 6.3765. Min Act: -0.1700
Data Index: 5066926 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5015. Min Range: -6.5015
Max Act: 6.3452. Min Act: -0.1700
Data Index: 1378410 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5015. Min Range: -6.5015
Max Act: 6.2827. Min Act: -0.1700
Data Index: 530987 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5015. Min Range: -6.5015
Max Act: 6.3140. Min Act: -0.1700
Data Index: 966402 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5015. Min Range: -6.5015
Max Act: 6.2827. Min Act: -0.1700
Data Index: 3948142 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5015. Min Range: -6.5015
Max Act: 6.3140. Min Act: -0.1700
Data Index: 5829034 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5015. Min Range: -6.5015
Max Act: 6.2827. Min Act: -0.1700
Data Index: 8709801 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5015. Min Range: -6.5015
Max Act: 6.2515. Min Act: -0.1700
Data Index: 8098839 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5015. Min Range: -6.5015
Max Act: 6.2515. Min Act: -0.1700
Data Index: 71994 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5015. Min Range: -6.5015
Max Act: 6.2202. Min Act: -0.1700
Data Index: 8660450 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5015. Min Range: -6.5015
Max Act: 6.2515. Min Act: -0.1700
Data Index: 5789225 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19