Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2705 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8399. Min Range: -7.8399
Max Act: 7.8399. Min Act: -0.1700
Data Index: 8077930 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8399. Min Range: -7.8399
Max Act: 7.7149. Min Act: -0.1700
Data Index: 6364857 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8399. Min Range: -7.8399
Max Act: 7.5899. Min Act: -0.1700
Data Index: 8782216 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8399. Min Range: -7.8399
Max Act: 7.5274. Min Act: -0.1700
Data Index: 8259023 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8399. Min Range: -7.8399
Max Act: 7.4649. Min Act: -0.1700
Data Index: 5682710 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8399. Min Range: -7.8399
Max Act: 7.5274. Min Act: -0.1700
Data Index: 3622861 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8399. Min Range: -7.8399
Max Act: 7.4649. Min Act: -0.1700
Data Index: 2411443 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8399. Min Range: -7.8399
Max Act: 7.4024. Min Act: -0.1700
Data Index: 5039678 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8399. Min Range: -7.8399
Max Act: 7.4024. Min Act: -0.1700
Data Index: 7270639 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8399. Min Range: -7.8399
Max Act: 7.3712. Min Act: -0.1700
Data Index: 7612364 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8399. Min Range: -7.8399
Max Act: 7.3399. Min Act: -0.1700
Data Index: 5149068 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8399. Min Range: -7.8399
Max Act: 7.2774. Min Act: -0.1700
Data Index: 345064 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8399. Min Range: -7.8399
Max Act: 7.2774. Min Act: -0.1700
Data Index: 1255920 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8399. Min Range: -7.8399
Max Act: 7.3087. Min Act: -0.1700
Data Index: 6186454 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8399. Min Range: -7.8399
Max Act: 7.2774. Min Act: -0.1700
Data Index: 620857 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8399. Min Range: -7.8399
Max Act: 7.3087. Min Act: -0.1700
Data Index: 8775387 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8399. Min Range: -7.8399
Max Act: 7.2774. Min Act: -0.1700
Data Index: 238692 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8399. Min Range: -7.8399
Max Act: 7.2462. Min Act: -0.1700
Data Index: 4579537 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8399. Min Range: -7.8399
Max Act: 7.2774. Min Act: -0.1700
Data Index: 5154425 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8399. Min Range: -7.8399
Max Act: 7.2462. Min Act: -0.1700
Data Index: 2254477 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19