Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 466 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3984. Min Range: -6.3984
Max Act: 6.3984. Min Act: -0.1700
Data Index: 1097340 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3984. Min Range: -6.3984
Max Act: 6.3046. Min Act: -0.1700
Data Index: 2631736 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3984. Min Range: -6.3984
Max Act: 6.2109. Min Act: -0.1700
Data Index: 1816483 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3984. Min Range: -6.3984
Max Act: 6.2109. Min Act: -0.1700
Data Index: 2293233 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3984. Min Range: -6.3984
Max Act: 6.2109. Min Act: -0.1700
Data Index: 1929852 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3984. Min Range: -6.3984
Max Act: 6.1171. Min Act: -0.1700
Data Index: 5954618 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3984. Min Range: -6.3984
Max Act: 6.0546. Min Act: -0.1700
Data Index: 8293278 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3984. Min Range: -6.3984
Max Act: 6.0234. Min Act: -0.1700
Data Index: 3676223 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3984. Min Range: -6.3984
Max Act: 6.0234. Min Act: -0.1700
Data Index: 5954617 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3984. Min Range: -6.3984
Max Act: 6.0234. Min Act: -0.1700
Data Index: 2963625 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3984. Min Range: -6.3984
Max Act: 5.9609. Min Act: -0.1700
Data Index: 1251422 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3984. Min Range: -6.3984
Max Act: 5.9609. Min Act: -0.1700
Data Index: 4470489 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3984. Min Range: -6.3984
Max Act: 5.9609. Min Act: -0.1700
Data Index: 7136771 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3984. Min Range: -6.3984
Max Act: 5.9296. Min Act: -0.1700
Data Index: 384766 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3984. Min Range: -6.3984
Max Act: 5.8671. Min Act: -0.1700
Data Index: 3098678 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3984. Min Range: -6.3984
Max Act: 5.8984. Min Act: -0.1700
Data Index: 4258645 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3984. Min Range: -6.3984
Max Act: 5.8671. Min Act: -0.1700
Data Index: 5575587 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3984. Min Range: -6.3984
Max Act: 5.8359. Min Act: -0.1700
Data Index: 1107671 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3984. Min Range: -6.3984
Max Act: 5.8359. Min Act: -0.1700
Data Index: 5959892 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3984. Min Range: -6.3984
Max Act: 5.8984. Min Act: -0.1700
Data Index: 323944 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19