Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 477 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2698. Min Range: -4.2698
Max Act: 4.2698. Min Act: -0.1700
Data Index: 453999 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2698. Min Range: -4.2698
Max Act: 4.1135. Min Act: -0.1700
Data Index: 2324019 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2698. Min Range: -4.2698
Max Act: 4.0823. Min Act: -0.1700
Data Index: 3495642 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2698. Min Range: -4.2698
Max Act: 4.0823. Min Act: -0.1700
Data Index: 5310019 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2698. Min Range: -4.2698
Max Act: 4.0823. Min Act: -0.1700
Data Index: 3651538 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2698. Min Range: -4.2698
Max Act: 4.0354. Min Act: -0.1700
Data Index: 3424100 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2698. Min Range: -4.2698
Max Act: 4.0354. Min Act: -0.1700
Data Index: 359966 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2698. Min Range: -4.2698
Max Act: 4.0354. Min Act: -0.1700
Data Index: 3685211 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2698. Min Range: -4.2698
Max Act: 4.0041. Min Act: -0.1700
Data Index: 5415333 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2698. Min Range: -4.2698
Max Act: 3.9885. Min Act: -0.1700
Data Index: 1445750 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2698. Min Range: -4.2698
Max Act: 3.9885. Min Act: -0.1700
Data Index: 6438489 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2698. Min Range: -4.2698
Max Act: 3.9729. Min Act: -0.1700
Data Index: 4216038 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2698. Min Range: -4.2698
Max Act: 3.9572. Min Act: -0.1700
Data Index: 3417882 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2698. Min Range: -4.2698
Max Act: 3.9572. Min Act: -0.1700
Data Index: 6994498 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2698. Min Range: -4.2698
Max Act: 3.9572. Min Act: -0.1700
Data Index: 4336140 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2698. Min Range: -4.2698
Max Act: 3.9572. Min Act: -0.1700
Data Index: 5237419 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2698. Min Range: -4.2698
Max Act: 3.9572. Min Act: -0.1700
Data Index: 2397410 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2698. Min Range: -4.2698
Max Act: 3.9416. Min Act: -0.1700
Data Index: 2972484 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2698. Min Range: -4.2698
Max Act: 3.9416. Min Act: -0.1700
Data Index: 29807 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2698. Min Range: -4.2698
Max Act: 3.9260. Min Act: -0.1700
Data Index: 1528434 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19