Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4535 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5155. Min Range: -3.5155
Max Act: 3.5155. Min Act: -0.1700
Data Index: 3223413 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5155. Min Range: -3.5155
Max Act: 3.4215. Min Act: -0.1700
Data Index: 1330916 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5155. Min Range: -3.5155
Max Act: 3.4058. Min Act: -0.1700
Data Index: 6458551 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5155. Min Range: -3.5155
Max Act: 3.2960. Min Act: -0.1700
Data Index: 7557538 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5155. Min Range: -3.5155
Max Act: 3.3117. Min Act: -0.1700
Data Index: 5329799 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5155. Min Range: -3.5155
Max Act: 3.2646. Min Act: -0.1700
Data Index: 761282 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5155. Min Range: -3.5155
Max Act: 3.2489. Min Act: -0.1700
Data Index: 5082389 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5155. Min Range: -3.5155
Max Act: 3.2175. Min Act: -0.1700
Data Index: 5372568 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5155. Min Range: -3.5155
Max Act: 3.2175. Min Act: -0.1700
Data Index: 1052400 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5155. Min Range: -3.5155
Max Act: 3.2175. Min Act: -0.1700
Data Index: 376338 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5155. Min Range: -3.5155
Max Act: 3.2175. Min Act: -0.1700
Data Index: 6741021 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5155. Min Range: -3.5155
Max Act: 3.2018. Min Act: -0.1700
Data Index: 2134222 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5155. Min Range: -3.5155
Max Act: 3.1860. Min Act: -0.1700
Data Index: 7487387 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5155. Min Range: -3.5155
Max Act: 3.2018. Min Act: -0.1700
Data Index: 4660753 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5155. Min Range: -3.5155
Max Act: 3.1860. Min Act: -0.1700
Data Index: 130721 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5155. Min Range: -3.5155
Max Act: 3.1860. Min Act: -0.1700
Data Index: 3326125 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5155. Min Range: -3.5155
Max Act: 3.2175. Min Act: -0.1700
Data Index: 4799078 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5155. Min Range: -3.5155
Max Act: 3.1703. Min Act: -0.1700
Data Index: 3166105 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5155. Min Range: -3.5155
Max Act: 3.2018. Min Act: -0.1700
Data Index: 2123261 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5155. Min Range: -3.5155
Max Act: 3.2018. Min Act: -0.1700
Data Index: 1045062 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19