Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2452. Min Range: -7.2452
Max Act: 7.2452. Min Act: -0.1700
Data Index: 4832127 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2452. Min Range: -7.2452
Max Act: 7.1827. Min Act: -0.1700
Data Index: 4832143 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2452. Min Range: -7.2452
Max Act: 6.9015. Min Act: -0.1700
Data Index: 1153948 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2452. Min Range: -7.2452
Max Act: 6.5577. Min Act: -0.1700
Data Index: 4832146 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2452. Min Range: -7.2452
Max Act: 6.4952. Min Act: -0.1700
Data Index: 4832130 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2452. Min Range: -7.2452
Max Act: 6.3702. Min Act: -0.1700
Data Index: 4832120 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2452. Min Range: -7.2452
Max Act: 6.2765. Min Act: -0.1700
Data Index: 1153947 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2452. Min Range: -7.2452
Max Act: 6.3390. Min Act: -0.1700
Data Index: 4832136 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2452. Min Range: -7.2452
Max Act: 6.2765. Min Act: -0.1700
Data Index: 348365 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2452. Min Range: -7.2452
Max Act: 6.2765. Min Act: -0.1700
Data Index: 7039214 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2452. Min Range: -7.2452
Max Act: 6.2452. Min Act: -0.1700
Data Index: 7622368 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2452. Min Range: -7.2452
Max Act: 6.2140. Min Act: -0.1700
Data Index: 1153945 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2452. Min Range: -7.2452
Max Act: 6.1827. Min Act: -0.1700
Data Index: 348347 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2452. Min Range: -7.2452
Max Act: 6.2140. Min Act: -0.1700
Data Index: 348367 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2452. Min Range: -7.2452
Max Act: 6.1515. Min Act: -0.1700
Data Index: 3480285 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2452. Min Range: -7.2452
Max Act: 6.1827. Min Act: -0.1700
Data Index: 7622376 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2452. Min Range: -7.2452
Max Act: 6.1827. Min Act: -0.1700
Data Index: 4656600 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2452. Min Range: -7.2452
Max Act: 6.1202. Min Act: -0.1700
Data Index: 348368 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2452. Min Range: -7.2452
Max Act: 6.0890. Min Act: -0.1700
Data Index: 4832147 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2452. Min Range: -7.2452
Max Act: 6.1202. Min Act: -0.1700
Data Index: 4832131 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19