Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 357 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6942. Min Range: -5.6942
Max Act: 5.6942. Min Act: -0.1700
Data Index: 4522860 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6942. Min Range: -5.6942
Max Act: 5.6004. Min Act: -0.1700
Data Index: 8787179 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6942. Min Range: -5.6942
Max Act: 5.5067. Min Act: -0.1700
Data Index: 2214123 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6942. Min Range: -5.6942
Max Act: 5.5067. Min Act: -0.1700
Data Index: 1479871 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6942. Min Range: -5.6942
Max Act: 5.5379. Min Act: -0.1700
Data Index: 5164783 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6942. Min Range: -5.6942
Max Act: 5.5379. Min Act: -0.1700
Data Index: 4529826 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6942. Min Range: -5.6942
Max Act: 5.4754. Min Act: -0.1700
Data Index: 2834720 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6942. Min Range: -5.6942
Max Act: 5.4754. Min Act: -0.1700
Data Index: 8534442 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6942. Min Range: -5.6942
Max Act: 5.4754. Min Act: -0.1700
Data Index: 6718370 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6942. Min Range: -5.6942
Max Act: 5.4754. Min Act: -0.1700
Data Index: 3037671 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6942. Min Range: -5.6942
Max Act: 5.4754. Min Act: -0.1700
Data Index: 6943603 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6942. Min Range: -5.6942
Max Act: 5.4442. Min Act: -0.1700
Data Index: 8831582 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6942. Min Range: -5.6942
Max Act: 5.4129. Min Act: -0.1700
Data Index: 2536295 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6942. Min Range: -5.6942
Max Act: 5.4442. Min Act: -0.1700
Data Index: 2227355 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6942. Min Range: -5.6942
Max Act: 5.4442. Min Act: -0.1700
Data Index: 3165942 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6942. Min Range: -5.6942
Max Act: 5.4129. Min Act: -0.1700
Data Index: 2798997 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6942. Min Range: -5.6942
Max Act: 5.3817. Min Act: -0.1700
Data Index: 5283636 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6942. Min Range: -5.6942
Max Act: 5.3504. Min Act: -0.1700
Data Index: 7887236 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6942. Min Range: -5.6942
Max Act: 5.3817. Min Act: -0.1700
Data Index: 4894180 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6942. Min Range: -5.6942
Max Act: 5.3817. Min Act: -0.1700
Data Index: 881899 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19