Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2079 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6739. Min Range: -5.6739
Max Act: 5.6739. Min Act: -0.1700
Data Index: 4681953 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6739. Min Range: -5.6739
Max Act: 5.6114. Min Act: -0.1700
Data Index: 8808434 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6739. Min Range: -5.6739
Max Act: 5.5177. Min Act: -0.1700
Data Index: 1712129 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6739. Min Range: -5.6739
Max Act: 5.5177. Min Act: -0.1700
Data Index: 4617699 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6739. Min Range: -5.6739
Max Act: 5.4552. Min Act: -0.1700
Data Index: 4980591 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6739. Min Range: -5.6739
Max Act: 5.4552. Min Act: -0.1700
Data Index: 4052887 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6739. Min Range: -5.6739
Max Act: 5.4239. Min Act: -0.1700
Data Index: 4960970 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6739. Min Range: -5.6739
Max Act: 5.4239. Min Act: -0.1700
Data Index: 7076993 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6739. Min Range: -5.6739
Max Act: 5.3927. Min Act: -0.1700
Data Index: 3813419 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6739. Min Range: -5.6739
Max Act: 5.3927. Min Act: -0.1700
Data Index: 2059649 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6739. Min Range: -5.6739
Max Act: 5.3614. Min Act: -0.1700
Data Index: 1879527 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6739. Min Range: -5.6739
Max Act: 5.3302. Min Act: -0.1700
Data Index: 3242678 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6739. Min Range: -5.6739
Max Act: 5.3927. Min Act: -0.1700
Data Index: 2315718 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6739. Min Range: -5.6739
Max Act: 5.3614. Min Act: -0.1700
Data Index: 6247572 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6739. Min Range: -5.6739
Max Act: 5.3614. Min Act: -0.1700
Data Index: 2954484 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6739. Min Range: -5.6739
Max Act: 5.3614. Min Act: -0.1700
Data Index: 8784052 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6739. Min Range: -5.6739
Max Act: 5.2989. Min Act: -0.1700
Data Index: 2908044 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6739. Min Range: -5.6739
Max Act: 5.2989. Min Act: -0.1700
Data Index: 7024499 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6739. Min Range: -5.6739
Max Act: 5.2677. Min Act: -0.1700
Data Index: 3795321 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6739. Min Range: -5.6739
Max Act: 5.2677. Min Act: -0.1700
Data Index: 5500536 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19