Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9135. Min Range: -2.9135
Max Act: 2.9135. Min Act: -0.1700
Data Index: 1774462 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9135. Min Range: -2.9135
Max Act: 2.8817. Min Act: -0.1700
Data Index: 7631936 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9135. Min Range: -2.9135
Max Act: 2.8659. Min Act: -0.1700
Data Index: 966902 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9135. Min Range: -2.9135
Max Act: 2.8500. Min Act: -0.1700
Data Index: 5423401 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9135. Min Range: -2.9135
Max Act: 2.8500. Min Act: -0.1700
Data Index: 359535 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9135. Min Range: -2.9135
Max Act: 2.8341. Min Act: -0.1700
Data Index: 5698109 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9135. Min Range: -2.9135
Max Act: 2.8500. Min Act: -0.1700
Data Index: 3300665 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9135. Min Range: -2.9135
Max Act: 2.8500. Min Act: -0.1700
Data Index: 2279284 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9135. Min Range: -2.9135
Max Act: 2.8341. Min Act: -0.1700
Data Index: 8753664 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9135. Min Range: -2.9135
Max Act: 2.8500. Min Act: -0.1700
Data Index: 8151520 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9135. Min Range: -2.9135
Max Act: 2.8500. Min Act: -0.1700
Data Index: 395878 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9135. Min Range: -2.9135
Max Act: 2.8500. Min Act: -0.1700
Data Index: 3944027 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9135. Min Range: -2.9135
Max Act: 2.8341. Min Act: -0.1700
Data Index: 7230053 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9135. Min Range: -2.9135
Max Act: 2.8341. Min Act: -0.1700
Data Index: 2651106 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9135. Min Range: -2.9135
Max Act: 2.8341. Min Act: -0.1700
Data Index: 1508004 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9135. Min Range: -2.9135
Max Act: 2.8182. Min Act: -0.1700
Data Index: 2116367 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9135. Min Range: -2.9135
Max Act: 2.8182. Min Act: -0.1700
Data Index: 1322533 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9135. Min Range: -2.9135
Max Act: 2.8182. Min Act: -0.1700
Data Index: 5308472 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9135. Min Range: -2.9135
Max Act: 2.8023. Min Act: -0.1700
Data Index: 5982915 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9135. Min Range: -2.9135
Max Act: 2.8182. Min Act: -0.1700
Data Index: 6323579 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19