Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2000 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.6109. Min Act: -0.1700
Data Index: 4953026 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4859. Min Act: -0.1700
Data Index: 7514415 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.3609. Min Act: -0.1700
Data Index: 3213106 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.2984. Min Act: -0.1700
Data Index: 7185020 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.2984. Min Act: -0.1700
Data Index: 6200515 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.2046. Min Act: -0.1700
Data Index: 4690617 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.2359. Min Act: -0.1700
Data Index: 4698648 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.2359. Min Act: -0.1700
Data Index: 8094176 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.2359. Min Act: -0.1700
Data Index: 2231318 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.2046. Min Act: -0.1700
Data Index: 5008938 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.2046. Min Act: -0.1700
Data Index: 4436766 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.2046. Min Act: -0.1700
Data Index: 1331156 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.2359. Min Act: -0.1700
Data Index: 7577968 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.2359. Min Act: -0.1700
Data Index: 8772962 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.1734. Min Act: -0.1700
Data Index: 6085998 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.1734. Min Act: -0.1700
Data Index: 1319310 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.1421. Min Act: -0.1700
Data Index: 164677 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.1421. Min Act: -0.1700
Data Index: 8016876 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.1421. Min Act: -0.1700
Data Index: 1912117 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.1421. Min Act: -0.1700
Data Index: 1536779 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19