Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4802 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.9882. Min Act: -0.1700
Data Index: 3797189 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.7382. Min Act: -0.1700
Data Index: 123057 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.7694. Min Act: -0.1700
Data Index: 225144 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.7382. Min Act: -0.1700
Data Index: 5353933 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.7069. Min Act: -0.1700
Data Index: 8616288 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.5819. Min Act: -0.1700
Data Index: 3467692 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.6132. Min Act: -0.1700
Data Index: 4174825 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.6132. Min Act: -0.1700
Data Index: 6846711 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.5819. Min Act: -0.1700
Data Index: 7808816 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.5819. Min Act: -0.1700
Data Index: 2886650 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.5507. Min Act: -0.1700
Data Index: 7026503 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.4882. Min Act: -0.1700
Data Index: 2650135 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.5194. Min Act: -0.1700
Data Index: 5778406 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.5194. Min Act: -0.1700
Data Index: 7857708 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.4882. Min Act: -0.1700
Data Index: 1705585 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.5194. Min Act: -0.1700
Data Index: 4207128 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.4882. Min Act: -0.1700
Data Index: 271861 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.4569. Min Act: -0.1700
Data Index: 8405336 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.4257. Min Act: -0.1700
Data Index: 6485096 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.4569. Min Act: -0.1700
Data Index: 8657611 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19