Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3936 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5551. Min Range: -4.5551
Max Act: 4.5551. Min Act: -0.1700
Data Index: 8411867 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5551. Min Range: -4.5551
Max Act: 4.5551. Min Act: -0.1700
Data Index: 1756604 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5551. Min Range: -4.5551
Max Act: 4.5238. Min Act: -0.1700
Data Index: 647523 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5551. Min Range: -4.5551
Max Act: 4.4613. Min Act: -0.1700
Data Index: 2669148 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5551. Min Range: -4.5551
Max Act: 4.4301. Min Act: -0.1700
Data Index: 6719667 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5551. Min Range: -4.5551
Max Act: 4.3676. Min Act: -0.1700
Data Index: 3626805 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5551. Min Range: -4.5551
Max Act: 4.3676. Min Act: -0.1700
Data Index: 1902338 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5551. Min Range: -4.5551
Max Act: 4.3363. Min Act: -0.1700
Data Index: 958505 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5551. Min Range: -4.5551
Max Act: 4.3363. Min Act: -0.1700
Data Index: 8215535 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5551. Min Range: -4.5551
Max Act: 4.3676. Min Act: -0.1700
Data Index: 1357030 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5551. Min Range: -4.5551
Max Act: 4.3676. Min Act: -0.1700
Data Index: 8507436 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5551. Min Range: -4.5551
Max Act: 4.3050. Min Act: -0.1700
Data Index: 6764558 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5551. Min Range: -4.5551
Max Act: 4.3050. Min Act: -0.1700
Data Index: 4106643 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5551. Min Range: -4.5551
Max Act: 4.3050. Min Act: -0.1700
Data Index: 7363597 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5551. Min Range: -4.5551
Max Act: 4.2738. Min Act: -0.1700
Data Index: 4502512 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5551. Min Range: -4.5551
Max Act: 4.3050. Min Act: -0.1700
Data Index: 7962666 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5551. Min Range: -4.5551
Max Act: 4.2425. Min Act: -0.1700
Data Index: 2805856 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5551. Min Range: -4.5551
Max Act: 4.2738. Min Act: -0.1700
Data Index: 4748687 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5551. Min Range: -4.5551
Max Act: 4.2425. Min Act: -0.1700
Data Index: 5732282 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5551. Min Range: -4.5551
Max Act: 4.2113. Min Act: -0.1700
Data Index: 4914051 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19