Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 968 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9482. Min Range: -6.9482
Max Act: 6.9482. Min Act: -0.1700
Data Index: 5339120 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9482. Min Range: -6.9482
Max Act: 6.8857. Min Act: -0.1700
Data Index: 2922410 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9482. Min Range: -6.9482
Max Act: 6.8232. Min Act: -0.1700
Data Index: 3872156 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9482. Min Range: -6.9482
Max Act: 6.7607. Min Act: -0.1700
Data Index: 2778800 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9482. Min Range: -6.9482
Max Act: 6.7920. Min Act: -0.1700
Data Index: 4895757 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9482. Min Range: -6.9482
Max Act: 6.7607. Min Act: -0.1700
Data Index: 489201 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9482. Min Range: -6.9482
Max Act: 6.7607. Min Act: -0.1700
Data Index: 562294 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9482. Min Range: -6.9482
Max Act: 6.6982. Min Act: -0.1700
Data Index: 4073204 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9482. Min Range: -6.9482
Max Act: 6.6982. Min Act: -0.1700
Data Index: 7348250 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9482. Min Range: -6.9482
Max Act: 6.7295. Min Act: -0.1700
Data Index: 6543981 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9482. Min Range: -6.9482
Max Act: 6.6670. Min Act: -0.1700
Data Index: 2344745 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9482. Min Range: -6.9482
Max Act: 6.6357. Min Act: -0.1700
Data Index: 778635 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9482. Min Range: -6.9482
Max Act: 6.6670. Min Act: -0.1700
Data Index: 261753 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9482. Min Range: -6.9482
Max Act: 6.6357. Min Act: -0.1700
Data Index: 3446912 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9482. Min Range: -6.9482
Max Act: 6.6357. Min Act: -0.1700
Data Index: 8324628 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9482. Min Range: -6.9482
Max Act: 6.6357. Min Act: -0.1700
Data Index: 372049 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9482. Min Range: -6.9482
Max Act: 6.6045. Min Act: -0.1700
Data Index: 728676 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9482. Min Range: -6.9482
Max Act: 6.5732. Min Act: -0.1700
Data Index: 667578 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9482. Min Range: -6.9482
Max Act: 6.6045. Min Act: -0.1700
Data Index: 2074872 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9482. Min Range: -6.9482
Max Act: 6.5732. Min Act: -0.1700
Data Index: 8221439 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19