Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1838 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6452. Min Range: -8.6452
Max Act: 8.6452. Min Act: -0.1700
Data Index: 7672412 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6452. Min Range: -8.6452
Max Act: 8.5827. Min Act: -0.1700
Data Index: 4786695 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6452. Min Range: -8.6452
Max Act: 8.5202. Min Act: -0.1700
Data Index: 6387861 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6452. Min Range: -8.6452
Max Act: 8.4577. Min Act: -0.1700
Data Index: 472296 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6452. Min Range: -8.6452
Max Act: 8.4577. Min Act: -0.1700
Data Index: 42499 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6452. Min Range: -8.6452
Max Act: 8.3952. Min Act: -0.1700
Data Index: 5405690 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6452. Min Range: -8.6452
Max Act: 8.3327. Min Act: -0.1700
Data Index: 2040460 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6452. Min Range: -8.6452
Max Act: 8.3327. Min Act: -0.1700
Data Index: 5953371 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6452. Min Range: -8.6452
Max Act: 8.3952. Min Act: -0.1700
Data Index: 8279099 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6452. Min Range: -8.6452
Max Act: 8.3327. Min Act: -0.1700
Data Index: 3413154 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6452. Min Range: -8.6452
Max Act: 8.2702. Min Act: -0.1700
Data Index: 6745819 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6452. Min Range: -8.6452
Max Act: 8.2077. Min Act: -0.1700
Data Index: 4554748 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6452. Min Range: -8.6452
Max Act: 8.2077. Min Act: -0.1700
Data Index: 5007066 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6452. Min Range: -8.6452
Max Act: 8.2702. Min Act: -0.1700
Data Index: 5250808 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6452. Min Range: -8.6452
Max Act: 8.2077. Min Act: -0.1700
Data Index: 4554750 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6452. Min Range: -8.6452
Max Act: 8.2077. Min Act: -0.1700
Data Index: 6949637 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6452. Min Range: -8.6452
Max Act: 8.2077. Min Act: -0.1700
Data Index: 8209066 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6452. Min Range: -8.6452
Max Act: 8.1452. Min Act: -0.1700
Data Index: 1776755 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6452. Min Range: -8.6452
Max Act: 8.1452. Min Act: -0.1700
Data Index: 5325024 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6452. Min Range: -8.6452
Max Act: 8.1452. Min Act: -0.1700
Data Index: 5555510 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19