Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2377 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3396. Min Range: -5.3396
Max Act: 5.3396. Min Act: -0.1700
Data Index: 7721379 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3396. Min Range: -5.3396
Max Act: 5.3084. Min Act: -0.1700
Data Index: 817223 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3396. Min Range: -5.3396
Max Act: 5.2771. Min Act: -0.1700
Data Index: 2450204 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3396. Min Range: -5.3396
Max Act: 5.1834. Min Act: -0.1700
Data Index: 1832836 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3396. Min Range: -5.3396
Max Act: 5.1209. Min Act: -0.1700
Data Index: 1445463 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3396. Min Range: -5.3396
Max Act: 5.0896. Min Act: -0.1700
Data Index: 7886873 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3396. Min Range: -5.3396
Max Act: 5.0584. Min Act: -0.1700
Data Index: 3732354 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3396. Min Range: -5.3396
Max Act: 5.0584. Min Act: -0.1700
Data Index: 5588173 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3396. Min Range: -5.3396
Max Act: 5.0584. Min Act: -0.1700
Data Index: 5733955 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3396. Min Range: -5.3396
Max Act: 5.0584. Min Act: -0.1700
Data Index: 3221212 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3396. Min Range: -5.3396
Max Act: 5.0896. Min Act: -0.1700
Data Index: 5864489 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3396. Min Range: -5.3396
Max Act: 5.0584. Min Act: -0.1700
Data Index: 4559797 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3396. Min Range: -5.3396
Max Act: 4.9959. Min Act: -0.1700
Data Index: 5564048 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3396. Min Range: -5.3396
Max Act: 5.0271. Min Act: -0.1700
Data Index: 688071 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3396. Min Range: -5.3396
Max Act: 4.9959. Min Act: -0.1700
Data Index: 1602101 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3396. Min Range: -5.3396
Max Act: 5.0271. Min Act: -0.1700
Data Index: 3610311 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3396. Min Range: -5.3396
Max Act: 5.0271. Min Act: -0.1700
Data Index: 4416280 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3396. Min Range: -5.3396
Max Act: 4.9959. Min Act: -0.1700
Data Index: 6141324 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3396. Min Range: -5.3396
Max Act: 4.9959. Min Act: -0.1700
Data Index: 7332608 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3396. Min Range: -5.3396
Max Act: 5.0271. Min Act: -0.1700
Data Index: 5873840 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19