Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 357 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6448. Min Range: -2.6448
Max Act: 2.6448. Min Act: -0.1700
Data Index: 5561766 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6448. Min Range: -2.6448
Max Act: 2.6448. Min Act: -0.1700
Data Index: 6178576 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6448. Min Range: -2.6448
Max Act: 2.6126. Min Act: -0.1700
Data Index: 8449215 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6448. Min Range: -2.6448
Max Act: 2.5966. Min Act: -0.1700
Data Index: 7642631 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6448. Min Range: -2.6448
Max Act: 2.6448. Min Act: -0.1700
Data Index: 4490047 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6448. Min Range: -2.6448
Max Act: 2.6287. Min Act: -0.1700
Data Index: 8816765 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6448. Min Range: -2.6448
Max Act: 2.5966. Min Act: -0.1700
Data Index: 324314 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6448. Min Range: -2.6448
Max Act: 2.6126. Min Act: -0.1700
Data Index: 3648929 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6448. Min Range: -2.6448
Max Act: 2.5966. Min Act: -0.1700
Data Index: 3990708 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6448. Min Range: -2.6448
Max Act: 2.5805. Min Act: -0.1700
Data Index: 1578330 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6448. Min Range: -2.6448
Max Act: 2.5643. Min Act: -0.1700
Data Index: 7006981 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6448. Min Range: -2.6448
Max Act: 2.5643. Min Act: -0.1700
Data Index: 4787946 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6448. Min Range: -2.6448
Max Act: 2.5482. Min Act: -0.1700
Data Index: 225107 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6448. Min Range: -2.6448
Max Act: 2.5482. Min Act: -0.1700
Data Index: 7990187 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6448. Min Range: -2.6448
Max Act: 2.5482. Min Act: -0.1700
Data Index: 3302692 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6448. Min Range: -2.6448
Max Act: 2.5320. Min Act: -0.1700
Data Index: 2268230 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6448. Min Range: -2.6448
Max Act: 2.5159. Min Act: -0.1700
Data Index: 29248 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6448. Min Range: -2.6448
Max Act: 2.5320. Min Act: -0.1700
Data Index: 125910 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6448. Min Range: -2.6448
Max Act: 2.5482. Min Act: -0.1700
Data Index: 3431330 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6448. Min Range: -2.6448
Max Act: 2.5320. Min Act: -0.1700
Data Index: 2311050 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19