Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2592 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9584. Min Range: -7.9584
Max Act: 7.9584. Min Act: -0.1700
Data Index: 988483 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9584. Min Range: -7.9584
Max Act: 7.7397. Min Act: -0.1700
Data Index: 8018340 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9584. Min Range: -7.9584
Max Act: 7.7084. Min Act: -0.1700
Data Index: 7542151 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9584. Min Range: -7.9584
Max Act: 7.6147. Min Act: -0.1700
Data Index: 5674992 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9584. Min Range: -7.9584
Max Act: 7.6459. Min Act: -0.1700
Data Index: 5784215 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9584. Min Range: -7.9584
Max Act: 7.5522. Min Act: -0.1700
Data Index: 3684520 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9584. Min Range: -7.9584
Max Act: 7.5522. Min Act: -0.1700
Data Index: 2041212 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9584. Min Range: -7.9584
Max Act: 7.5522. Min Act: -0.1700
Data Index: 5784214 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9584. Min Range: -7.9584
Max Act: 7.5209. Min Act: -0.1700
Data Index: 4184827 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9584. Min Range: -7.9584
Max Act: 7.4584. Min Act: -0.1700
Data Index: 8428571 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9584. Min Range: -7.9584
Max Act: 7.4897. Min Act: -0.1700
Data Index: 5129517 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9584. Min Range: -7.9584
Max Act: 7.4897. Min Act: -0.1700
Data Index: 227945 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9584. Min Range: -7.9584
Max Act: 7.5209. Min Act: -0.1700
Data Index: 5829898 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9584. Min Range: -7.9584
Max Act: 7.4584. Min Act: -0.1700
Data Index: 4080007 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9584. Min Range: -7.9584
Max Act: 7.4897. Min Act: -0.1700
Data Index: 1776150 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9584. Min Range: -7.9584
Max Act: 7.4584. Min Act: -0.1700
Data Index: 339737 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9584. Min Range: -7.9584
Max Act: 7.4584. Min Act: -0.1700
Data Index: 5784216 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9584. Min Range: -7.9584
Max Act: 7.4584. Min Act: -0.1700
Data Index: 3895995 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9584. Min Range: -7.9584
Max Act: 7.4584. Min Act: -0.1700
Data Index: 5523922 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9584. Min Range: -7.9584
Max Act: 7.4897. Min Act: -0.1700
Data Index: 8398319 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19