Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4924 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7795. Min Range: -6.7795
Max Act: 6.7795. Min Act: -0.1700
Data Index: 5381626 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7795. Min Range: -6.7795
Max Act: 6.5920. Min Act: -0.1700
Data Index: 5421025 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7795. Min Range: -6.7795
Max Act: 6.5607. Min Act: -0.1700
Data Index: 541619 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7795. Min Range: -6.7795
Max Act: 6.5607. Min Act: -0.1700
Data Index: 6498517 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7795. Min Range: -6.7795
Max Act: 6.4982. Min Act: -0.1700
Data Index: 8751321 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7795. Min Range: -6.7795
Max Act: 6.4045. Min Act: -0.1700
Data Index: 8264611 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7795. Min Range: -6.7795
Max Act: 6.4357. Min Act: -0.1700
Data Index: 6216539 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7795. Min Range: -6.7795
Max Act: 6.3732. Min Act: -0.1700
Data Index: 4000538 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7795. Min Range: -6.7795
Max Act: 6.3732. Min Act: -0.1700
Data Index: 5104774 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7795. Min Range: -6.7795
Max Act: 6.3420. Min Act: -0.1700
Data Index: 7333390 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7795. Min Range: -6.7795
Max Act: 6.3420. Min Act: -0.1700
Data Index: 1235971 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7795. Min Range: -6.7795
Max Act: 6.3107. Min Act: -0.1700
Data Index: 7525904 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7795. Min Range: -6.7795
Max Act: 6.2795. Min Act: -0.1700
Data Index: 7717776 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7795. Min Range: -6.7795
Max Act: 6.2795. Min Act: -0.1700
Data Index: 7869705 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7795. Min Range: -6.7795
Max Act: 6.2482. Min Act: -0.1700
Data Index: 3626935 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7795. Min Range: -6.7795
Max Act: 6.2482. Min Act: -0.1700
Data Index: 36842 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7795. Min Range: -6.7795
Max Act: 6.2482. Min Act: -0.1700
Data Index: 8824048 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7795. Min Range: -6.7795
Max Act: 6.2170. Min Act: -0.1700
Data Index: 2018054 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7795. Min Range: -6.7795
Max Act: 6.2170. Min Act: -0.1700
Data Index: 7089006 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7795. Min Range: -6.7795
Max Act: 6.1857. Min Act: -0.1700
Data Index: 2900666 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19