Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3464 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3384. Min Range: -6.3384
Max Act: 6.3384. Min Act: -0.1700
Data Index: 1961163 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3384. Min Range: -6.3384
Max Act: 6.2447. Min Act: -0.1700
Data Index: 2766299 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3384. Min Range: -6.3384
Max Act: 6.2134. Min Act: -0.1700
Data Index: 2384876 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3384. Min Range: -6.3384
Max Act: 6.1197. Min Act: -0.1700
Data Index: 6766524 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3384. Min Range: -6.3384
Max Act: 6.0884. Min Act: -0.1700
Data Index: 2915894 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3384. Min Range: -6.3384
Max Act: 6.0572. Min Act: -0.1700
Data Index: 3668965 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3384. Min Range: -6.3384
Max Act: 6.0259. Min Act: -0.1700
Data Index: 3322827 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3384. Min Range: -6.3384
Max Act: 6.0572. Min Act: -0.1700
Data Index: 2233071 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3384. Min Range: -6.3384
Max Act: 5.9634. Min Act: -0.1700
Data Index: 4239491 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3384. Min Range: -6.3384
Max Act: 5.9634. Min Act: -0.1700
Data Index: 1194450 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3384. Min Range: -6.3384
Max Act: 5.9322. Min Act: -0.1700
Data Index: 4577381 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3384. Min Range: -6.3384
Max Act: 5.9009. Min Act: -0.1700
Data Index: 4599039 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3384. Min Range: -6.3384
Max Act: 5.9009. Min Act: -0.1700
Data Index: 3150065 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3384. Min Range: -6.3384
Max Act: 5.9009. Min Act: -0.1700
Data Index: 3262331 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3384. Min Range: -6.3384
Max Act: 5.8697. Min Act: -0.1700
Data Index: 3688213 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3384. Min Range: -6.3384
Max Act: 5.8697. Min Act: -0.1700
Data Index: 8036421 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3384. Min Range: -6.3384
Max Act: 5.8697. Min Act: -0.1700
Data Index: 3923737 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3384. Min Range: -6.3384
Max Act: 5.8072. Min Act: -0.1700
Data Index: 5922836 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3384. Min Range: -6.3384
Max Act: 5.8072. Min Act: -0.1700
Data Index: 34476 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3384. Min Range: -6.3384
Max Act: 5.7447. Min Act: -0.1700
Data Index: 815701 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19