Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2503 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1301. Min Range: -5.1301
Max Act: 5.1301. Min Act: -0.1700
Data Index: 5725355 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1301. Min Range: -5.1301
Max Act: 5.0988. Min Act: -0.1700
Data Index: 7939413 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1301. Min Range: -5.1301
Max Act: 4.9426. Min Act: -0.1700
Data Index: 7818973 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1301. Min Range: -5.1301
Max Act: 4.9426. Min Act: -0.1700
Data Index: 3456140 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1301. Min Range: -5.1301
Max Act: 4.8801. Min Act: -0.1700
Data Index: 2644739 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1301. Min Range: -5.1301
Max Act: 4.8488. Min Act: -0.1700
Data Index: 4568465 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1301. Min Range: -5.1301
Max Act: 4.8488. Min Act: -0.1700
Data Index: 8169736 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1301. Min Range: -5.1301
Max Act: 4.7863. Min Act: -0.1700
Data Index: 5236676 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1301. Min Range: -5.1301
Max Act: 4.7551. Min Act: -0.1700
Data Index: 8664141 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1301. Min Range: -5.1301
Max Act: 4.7863. Min Act: -0.1700
Data Index: 5755739 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1301. Min Range: -5.1301
Max Act: 4.7863. Min Act: -0.1700
Data Index: 4147693 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1301. Min Range: -5.1301
Max Act: 4.7238. Min Act: -0.1700
Data Index: 287545 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1301. Min Range: -5.1301
Max Act: 4.7238. Min Act: -0.1700
Data Index: 4894970 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1301. Min Range: -5.1301
Max Act: 4.7238. Min Act: -0.1700
Data Index: 6051166 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1301. Min Range: -5.1301
Max Act: 4.7551. Min Act: -0.1700
Data Index: 2819326 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1301. Min Range: -5.1301
Max Act: 4.6926. Min Act: -0.1700
Data Index: 5003406 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1301. Min Range: -5.1301
Max Act: 4.7238. Min Act: -0.1700
Data Index: 2598618 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1301. Min Range: -5.1301
Max Act: 4.7238. Min Act: -0.1700
Data Index: 7449339 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1301. Min Range: -5.1301
Max Act: 4.7551. Min Act: -0.1700
Data Index: 747441 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1301. Min Range: -5.1301
Max Act: 4.7238. Min Act: -0.1700
Data Index: 4119036 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19