Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4224 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5305. Min Range: -6.5305
Max Act: 6.5305. Min Act: -0.1700
Data Index: 6715121 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5305. Min Range: -6.5305
Max Act: 6.4992. Min Act: -0.1700
Data Index: 5697540 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5305. Min Range: -6.5305
Max Act: 6.3117. Min Act: -0.1700
Data Index: 1102354 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5305. Min Range: -6.5305
Max Act: 6.1555. Min Act: -0.1700
Data Index: 8216397 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5305. Min Range: -6.5305
Max Act: 6.0617. Min Act: -0.1700
Data Index: 1096309 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5305. Min Range: -6.5305
Max Act: 5.9992. Min Act: -0.1700
Data Index: 7468692 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5305. Min Range: -6.5305
Max Act: 5.9680. Min Act: -0.1700
Data Index: 5163749 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5305. Min Range: -6.5305
Max Act: 5.9680. Min Act: -0.1700
Data Index: 8090765 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5305. Min Range: -6.5305
Max Act: 5.9680. Min Act: -0.1700
Data Index: 5954300 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5305. Min Range: -6.5305
Max Act: 5.9367. Min Act: -0.1700
Data Index: 4790672 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5305. Min Range: -6.5305
Max Act: 5.9055. Min Act: -0.1700
Data Index: 532393 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5305. Min Range: -6.5305
Max Act: 5.8742. Min Act: -0.1700
Data Index: 1614859 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5305. Min Range: -6.5305
Max Act: 5.8117. Min Act: -0.1700
Data Index: 284655 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5305. Min Range: -6.5305
Max Act: 5.8430. Min Act: -0.1700
Data Index: 5751549 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5305. Min Range: -6.5305
Max Act: 5.8430. Min Act: -0.1700
Data Index: 5127195 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5305. Min Range: -6.5305
Max Act: 5.8117. Min Act: -0.1700
Data Index: 6368158 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5305. Min Range: -6.5305
Max Act: 5.8117. Min Act: -0.1700
Data Index: 6964016 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5305. Min Range: -6.5305
Max Act: 5.7805. Min Act: -0.1700
Data Index: 3376074 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5305. Min Range: -6.5305
Max Act: 5.7805. Min Act: -0.1700
Data Index: 4505199 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5305. Min Range: -6.5305
Max Act: 5.7805. Min Act: -0.1700
Data Index: 4978663 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19