Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3616 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1738. Min Range: -7.1738
Max Act: 7.1738. Min Act: -0.1700
Data Index: 8797983 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1738. Min Range: -7.1738
Max Act: 7.0801. Min Act: -0.1700
Data Index: 6569803 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1738. Min Range: -7.1738
Max Act: 7.0801. Min Act: -0.1700
Data Index: 7380751 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1738. Min Range: -7.1738
Max Act: 6.9863. Min Act: -0.1700
Data Index: 2649174 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1738. Min Range: -7.1738
Max Act: 7.0176. Min Act: -0.1700
Data Index: 4817144 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1738. Min Range: -7.1738
Max Act: 6.9863. Min Act: -0.1700
Data Index: 2265579 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1738. Min Range: -7.1738
Max Act: 6.9863. Min Act: -0.1700
Data Index: 8614201 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1738. Min Range: -7.1738
Max Act: 6.9863. Min Act: -0.1700
Data Index: 1526622 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1738. Min Range: -7.1738
Max Act: 6.9551. Min Act: -0.1700
Data Index: 8282522 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1738. Min Range: -7.1738
Max Act: 6.8613. Min Act: -0.1700
Data Index: 3946027 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1738. Min Range: -7.1738
Max Act: 6.8301. Min Act: -0.1700
Data Index: 8685673 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1738. Min Range: -7.1738
Max Act: 6.8301. Min Act: -0.1700
Data Index: 4847612 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1738. Min Range: -7.1738
Max Act: 6.7676. Min Act: -0.1700
Data Index: 273354 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1738. Min Range: -7.1738
Max Act: 6.7676. Min Act: -0.1700
Data Index: 1370103 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1738. Min Range: -7.1738
Max Act: 6.7363. Min Act: -0.1700
Data Index: 6656457 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1738. Min Range: -7.1738
Max Act: 6.7363. Min Act: -0.1700
Data Index: 6418583 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1738. Min Range: -7.1738
Max Act: 6.7363. Min Act: -0.1700
Data Index: 5946011 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1738. Min Range: -7.1738
Max Act: 6.7363. Min Act: -0.1700
Data Index: 4109590 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1738. Min Range: -7.1738
Max Act: 6.7676. Min Act: -0.1700
Data Index: 631363 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1738. Min Range: -7.1738
Max Act: 6.7051. Min Act: -0.1700
Data Index: 894436 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19