Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2625 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9380. Min Range: -1.9380
Max Act: 1.9380. Min Act: -0.1700
Data Index: 319798 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9380. Min Range: -1.9380
Max Act: 1.9210. Min Act: -0.1700
Data Index: 3795092 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9380. Min Range: -1.9380
Max Act: 1.9040. Min Act: -0.1700
Data Index: 1978325 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9380. Min Range: -1.9380
Max Act: 1.8356. Min Act: -0.1700
Data Index: 3795094 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9380. Min Range: -1.9380
Max Act: 1.8270. Min Act: -0.1700
Data Index: 8511985 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9380. Min Range: -1.9380
Max Act: 1.8270. Min Act: -0.1700
Data Index: 6844162 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9380. Min Range: -1.9380
Max Act: 1.8184. Min Act: -0.1700
Data Index: 4982393 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9380. Min Range: -1.9380
Max Act: 1.8098. Min Act: -0.1700
Data Index: 2544607 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9380. Min Range: -1.9380
Max Act: 1.8098. Min Act: -0.1700
Data Index: 1653975 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9380. Min Range: -1.9380
Max Act: 1.8098. Min Act: -0.1700
Data Index: 4578089 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9380. Min Range: -1.9380
Max Act: 1.8098. Min Act: -0.1700
Data Index: 1958269 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9380. Min Range: -1.9380
Max Act: 1.7840. Min Act: -0.1700
Data Index: 698516 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9380. Min Range: -1.9380
Max Act: 1.7754. Min Act: -0.1700
Data Index: 1871026 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9380. Min Range: -1.9380
Max Act: 1.7754. Min Act: -0.1700
Data Index: 1516325 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9380. Min Range: -1.9380
Max Act: 1.7754. Min Act: -0.1700
Data Index: 2936814 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9380. Min Range: -1.9380
Max Act: 1.7754. Min Act: -0.1700
Data Index: 1034166 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9380. Min Range: -1.9380
Max Act: 1.7926. Min Act: -0.1700
Data Index: 5630809 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9380. Min Range: -1.9380
Max Act: 1.7754. Min Act: -0.1700
Data Index: 6087344 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9380. Min Range: -1.9380
Max Act: 1.7754. Min Act: -0.1700
Data Index: 6765384 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9380. Min Range: -1.9380
Max Act: 1.7754. Min Act: -0.1700
Data Index: 7638003 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19