Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3098 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8044. Min Range: -6.8044
Max Act: 6.8044. Min Act: -0.1700
Data Index: 3300822 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8044. Min Range: -6.8044
Max Act: 6.4919. Min Act: -0.1700
Data Index: 4313246 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8044. Min Range: -6.8044
Max Act: 6.4607. Min Act: -0.1700
Data Index: 8522341 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8044. Min Range: -6.8044
Max Act: 6.4294. Min Act: -0.1700
Data Index: 2015544 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8044. Min Range: -6.8044
Max Act: 6.2732. Min Act: -0.1700
Data Index: 7958554 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8044. Min Range: -6.8044
Max Act: 6.1794. Min Act: -0.1700
Data Index: 4366112 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8044. Min Range: -6.8044
Max Act: 6.1482. Min Act: -0.1700
Data Index: 3424838 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8044. Min Range: -6.8044
Max Act: 6.1169. Min Act: -0.1700
Data Index: 5457774 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8044. Min Range: -6.8044
Max Act: 6.1169. Min Act: -0.1700
Data Index: 2331839 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8044. Min Range: -6.8044
Max Act: 6.1169. Min Act: -0.1700
Data Index: 6100787 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8044. Min Range: -6.8044
Max Act: 6.1169. Min Act: -0.1700
Data Index: 946759 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8044. Min Range: -6.8044
Max Act: 6.1169. Min Act: -0.1700
Data Index: 1798207 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8044. Min Range: -6.8044
Max Act: 6.0544. Min Act: -0.1700
Data Index: 4430248 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8044. Min Range: -6.8044
Max Act: 6.0232. Min Act: -0.1700
Data Index: 5255627 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8044. Min Range: -6.8044
Max Act: 6.0232. Min Act: -0.1700
Data Index: 8604479 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8044. Min Range: -6.8044
Max Act: 6.0232. Min Act: -0.1700
Data Index: 4642401 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8044. Min Range: -6.8044
Max Act: 5.9919. Min Act: -0.1700
Data Index: 2958868 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8044. Min Range: -6.8044
Max Act: 5.9607. Min Act: -0.1700
Data Index: 7175841 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8044. Min Range: -6.8044
Max Act: 5.9919. Min Act: -0.1700
Data Index: 4520076 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8044. Min Range: -6.8044
Max Act: 5.9607. Min Act: -0.1700
Data Index: 1349003 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19