Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1772 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8294. Min Range: -4.8294
Max Act: 4.8294. Min Act: -0.1700
Data Index: 4076550 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8294. Min Range: -4.8294
Max Act: 4.7669. Min Act: -0.1700
Data Index: 3384893 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8294. Min Range: -4.8294
Max Act: 4.7982. Min Act: -0.1700
Data Index: 6110377 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8294. Min Range: -4.8294
Max Act: 4.7357. Min Act: -0.1700
Data Index: 797062 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8294. Min Range: -4.8294
Max Act: 4.7044. Min Act: -0.1700
Data Index: 5175385 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8294. Min Range: -4.8294
Max Act: 4.6732. Min Act: -0.1700
Data Index: 1960136 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8294. Min Range: -4.8294
Max Act: 4.6732. Min Act: -0.1700
Data Index: 5654088 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8294. Min Range: -4.8294
Max Act: 4.6732. Min Act: -0.1700
Data Index: 4008020 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8294. Min Range: -4.8294
Max Act: 4.6419. Min Act: -0.1700
Data Index: 1601406 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8294. Min Range: -4.8294
Max Act: 4.5169. Min Act: -0.1700
Data Index: 4779037 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8294. Min Range: -4.8294
Max Act: 4.4857. Min Act: -0.1700
Data Index: 1831643 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8294. Min Range: -4.8294
Max Act: 4.4857. Min Act: -0.1700
Data Index: 5097190 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8294. Min Range: -4.8294
Max Act: 4.4544. Min Act: -0.1700
Data Index: 4611165 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8294. Min Range: -4.8294
Max Act: 4.4544. Min Act: -0.1700
Data Index: 8511023 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8294. Min Range: -4.8294
Max Act: 4.4544. Min Act: -0.1700
Data Index: 3058333 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8294. Min Range: -4.8294
Max Act: 4.4544. Min Act: -0.1700
Data Index: 494817 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8294. Min Range: -4.8294
Max Act: 4.4544. Min Act: -0.1700
Data Index: 6556670 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8294. Min Range: -4.8294
Max Act: 4.4232. Min Act: -0.1700
Data Index: 5690606 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8294. Min Range: -4.8294
Max Act: 4.4232. Min Act: -0.1700
Data Index: 158067 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8294. Min Range: -4.8294
Max Act: 4.4544. Min Act: -0.1700
Data Index: 506301 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19