Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 638 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5452. Min Range: -3.5452
Max Act: 3.5452. Min Act: -0.1700
Data Index: 4480139 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5452. Min Range: -3.5452
Max Act: 3.5139. Min Act: -0.1700
Data Index: 1107138 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5452. Min Range: -3.5452
Max Act: 3.4982. Min Act: -0.1700
Data Index: 1776400 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5452. Min Range: -3.5452
Max Act: 3.4669. Min Act: -0.1700
Data Index: 8551901 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5452. Min Range: -3.5452
Max Act: 3.4199. Min Act: -0.1700
Data Index: 4637387 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5452. Min Range: -3.5452
Max Act: 3.3885. Min Act: -0.1700
Data Index: 3761481 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5452. Min Range: -3.5452
Max Act: 3.3885. Min Act: -0.1700
Data Index: 5346734 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5452. Min Range: -3.5452
Max Act: 3.3729. Min Act: -0.1700
Data Index: 1625697 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5452. Min Range: -3.5452
Max Act: 3.3415. Min Act: -0.1700
Data Index: 7344127 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5452. Min Range: -3.5452
Max Act: 3.3415. Min Act: -0.1700
Data Index: 724974 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5452. Min Range: -3.5452
Max Act: 3.3258. Min Act: -0.1700
Data Index: 8379949 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5452. Min Range: -3.5452
Max Act: 3.3258. Min Act: -0.1700
Data Index: 7285046 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5452. Min Range: -3.5452
Max Act: 3.2787. Min Act: -0.1700
Data Index: 4833294 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5452. Min Range: -3.5452
Max Act: 3.2630. Min Act: -0.1700
Data Index: 5622678 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5452. Min Range: -3.5452
Max Act: 3.2787. Min Act: -0.1700
Data Index: 6301860 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5452. Min Range: -3.5452
Max Act: 3.2787. Min Act: -0.1700
Data Index: 2643414 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5452. Min Range: -3.5452
Max Act: 3.2787. Min Act: -0.1700
Data Index: 7129531 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5452. Min Range: -3.5452
Max Act: 3.2630. Min Act: -0.1700
Data Index: 685473 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5452. Min Range: -3.5452
Max Act: 3.2787. Min Act: -0.1700
Data Index: 4639212 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5452. Min Range: -3.5452
Max Act: 3.2787. Min Act: -0.1700
Data Index: 3130393 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19