Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 857 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1393. Min Range: -4.1393
Max Act: 4.1393. Min Act: -0.1700
Data Index: 4302956 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1393. Min Range: -4.1393
Max Act: 4.1393. Min Act: -0.1700
Data Index: 7255280 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1393. Min Range: -4.1393
Max Act: 4.0768. Min Act: -0.1700
Data Index: 3547734 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1393. Min Range: -4.1393
Max Act: 4.0768. Min Act: -0.1700
Data Index: 2930687 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1393. Min Range: -4.1393
Max Act: 4.1081. Min Act: -0.1700
Data Index: 1202179 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1393. Min Range: -4.1393
Max Act: 4.1081. Min Act: -0.1700
Data Index: 5542589 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1393. Min Range: -4.1393
Max Act: 4.0143. Min Act: -0.1700
Data Index: 1582334 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1393. Min Range: -4.1393
Max Act: 4.0143. Min Act: -0.1700
Data Index: 7111004 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1393. Min Range: -4.1393
Max Act: 3.9518. Min Act: -0.1700
Data Index: 8804526 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1393. Min Range: -4.1393
Max Act: 3.9830. Min Act: -0.1700
Data Index: 6540583 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1393. Min Range: -4.1393
Max Act: 3.9830. Min Act: -0.1700
Data Index: 3494887 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1393. Min Range: -4.1393
Max Act: 3.9518. Min Act: -0.1700
Data Index: 1952124 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1393. Min Range: -4.1393
Max Act: 3.9205. Min Act: -0.1700
Data Index: 5359397 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1393. Min Range: -4.1393
Max Act: 3.9205. Min Act: -0.1700
Data Index: 2115620 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1393. Min Range: -4.1393
Max Act: 3.9205. Min Act: -0.1700
Data Index: 5859018 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1393. Min Range: -4.1393
Max Act: 3.9205. Min Act: -0.1700
Data Index: 8732474 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1393. Min Range: -4.1393
Max Act: 3.8580. Min Act: -0.1700
Data Index: 2316179 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1393. Min Range: -4.1393
Max Act: 3.7954. Min Act: -0.1700
Data Index: 1836516 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1393. Min Range: -4.1393
Max Act: 3.8580. Min Act: -0.1700
Data Index: 1740312 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1393. Min Range: -4.1393
Max Act: 3.8580. Min Act: -0.1700
Data Index: 2473022 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19