Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3878 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4248. Min Range: -3.4248
Max Act: 3.4248. Min Act: -0.1700
Data Index: 4511986 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4248. Min Range: -3.4248
Max Act: 3.3778. Min Act: -0.1700
Data Index: 6455429 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4248. Min Range: -3.4248
Max Act: 3.3464. Min Act: -0.1700
Data Index: 8099686 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4248. Min Range: -3.4248
Max Act: 3.2993. Min Act: -0.1700
Data Index: 4273512 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4248. Min Range: -3.4248
Max Act: 3.2993. Min Act: -0.1700
Data Index: 8396634 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4248. Min Range: -3.4248
Max Act: 3.2679. Min Act: -0.1700
Data Index: 71054 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4248. Min Range: -3.4248
Max Act: 3.2836. Min Act: -0.1700
Data Index: 611137 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4248. Min Range: -3.4248
Max Act: 3.2365. Min Act: -0.1700
Data Index: 4467014 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4248. Min Range: -3.4248
Max Act: 3.2522. Min Act: -0.1700
Data Index: 2896160 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4248. Min Range: -3.4248
Max Act: 3.2522. Min Act: -0.1700
Data Index: 1836005 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4248. Min Range: -3.4248
Max Act: 3.2365. Min Act: -0.1700
Data Index: 2613266 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4248. Min Range: -3.4248
Max Act: 3.2208. Min Act: -0.1700
Data Index: 6877229 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4248. Min Range: -3.4248
Max Act: 3.1736. Min Act: -0.1700
Data Index: 7553466 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4248. Min Range: -3.4248
Max Act: 3.1579. Min Act: -0.1700
Data Index: 5775724 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4248. Min Range: -3.4248
Max Act: 3.1579. Min Act: -0.1700
Data Index: 5247558 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4248. Min Range: -3.4248
Max Act: 3.1421. Min Act: -0.1700
Data Index: 906520 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4248. Min Range: -3.4248
Max Act: 3.1579. Min Act: -0.1700
Data Index: 7915675 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4248. Min Range: -3.4248
Max Act: 3.1421. Min Act: -0.1700
Data Index: 8152735 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4248. Min Range: -3.4248
Max Act: 3.1579. Min Act: -0.1700
Data Index: 1308334 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4248. Min Range: -3.4248
Max Act: 3.1421. Min Act: -0.1700
Data Index: 6508586 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19