Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1278 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3815. Min Range: -3.3815
Max Act: 3.3815. Min Act: -0.1700
Data Index: 2000758 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3815. Min Range: -3.3815
Max Act: 3.3501. Min Act: -0.1700
Data Index: 460044 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3815. Min Range: -3.3815
Max Act: 3.3815. Min Act: -0.1700
Data Index: 325975 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3815. Min Range: -3.3815
Max Act: 3.3031. Min Act: -0.1700
Data Index: 3320235 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3815. Min Range: -3.3815
Max Act: 3.3501. Min Act: -0.1700
Data Index: 672074 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3815. Min Range: -3.3815
Max Act: 3.3188. Min Act: -0.1700
Data Index: 6532688 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3815. Min Range: -3.3815
Max Act: 3.3188. Min Act: -0.1700
Data Index: 8041954 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3815. Min Range: -3.3815
Max Act: 3.3031. Min Act: -0.1700
Data Index: 3229027 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3815. Min Range: -3.3815
Max Act: 3.3031. Min Act: -0.1700
Data Index: 2027208 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3815. Min Range: -3.3815
Max Act: 3.3188. Min Act: -0.1700
Data Index: 5661611 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3815. Min Range: -3.3815
Max Act: 3.3031. Min Act: -0.1700
Data Index: 7995941 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3815. Min Range: -3.3815
Max Act: 3.3031. Min Act: -0.1700
Data Index: 5392543 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3815. Min Range: -3.3815
Max Act: 3.2874. Min Act: -0.1700
Data Index: 935739 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3815. Min Range: -3.3815
Max Act: 3.2874. Min Act: -0.1700
Data Index: 1482675 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3815. Min Range: -3.3815
Max Act: 3.3031. Min Act: -0.1700
Data Index: 2784446 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3815. Min Range: -3.3815
Max Act: 3.2874. Min Act: -0.1700
Data Index: 8477952 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3815. Min Range: -3.3815
Max Act: 3.2402. Min Act: -0.1700
Data Index: 3023802 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3815. Min Range: -3.3815
Max Act: 3.2717. Min Act: -0.1700
Data Index: 4725787 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3815. Min Range: -3.3815
Max Act: 3.2559. Min Act: -0.1700
Data Index: 3128578 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3815. Min Range: -3.3815
Max Act: 3.2717. Min Act: -0.1700
Data Index: 1017412 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19