Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3672 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6248. Min Range: -4.6248
Max Act: 4.6248. Min Act: -0.1700
Data Index: 5780023 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6248. Min Range: -4.6248
Max Act: 4.5623. Min Act: -0.1700
Data Index: 4110251 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6248. Min Range: -4.6248
Max Act: 4.4060. Min Act: -0.1700
Data Index: 6853762 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6248. Min Range: -4.6248
Max Act: 4.3123. Min Act: -0.1700
Data Index: 2840659 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6248. Min Range: -4.6248
Max Act: 4.2810. Min Act: -0.1700
Data Index: 3354499 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6248. Min Range: -4.6248
Max Act: 4.2810. Min Act: -0.1700
Data Index: 2615700 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6248. Min Range: -4.6248
Max Act: 4.2498. Min Act: -0.1700
Data Index: 2645220 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6248. Min Range: -4.6248
Max Act: 4.2498. Min Act: -0.1700
Data Index: 7114139 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6248. Min Range: -4.6248
Max Act: 4.2185. Min Act: -0.1700
Data Index: 5060496 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6248. Min Range: -4.6248
Max Act: 4.2185. Min Act: -0.1700
Data Index: 8495842 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6248. Min Range: -4.6248
Max Act: 4.2185. Min Act: -0.1700
Data Index: 312143 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6248. Min Range: -4.6248
Max Act: 4.2498. Min Act: -0.1700
Data Index: 4199929 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6248. Min Range: -4.6248
Max Act: 4.2185. Min Act: -0.1700
Data Index: 6395806 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6248. Min Range: -4.6248
Max Act: 4.1872. Min Act: -0.1700
Data Index: 6300180 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6248. Min Range: -4.6248
Max Act: 4.1872. Min Act: -0.1700
Data Index: 1362720 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6248. Min Range: -4.6248
Max Act: 4.1872. Min Act: -0.1700
Data Index: 178074 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6248. Min Range: -4.6248
Max Act: 4.1872. Min Act: -0.1700
Data Index: 7825983 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6248. Min Range: -4.6248
Max Act: 4.1872. Min Act: -0.1700
Data Index: 8142567 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6248. Min Range: -4.6248
Max Act: 4.1247. Min Act: -0.1700
Data Index: 3067151 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6248. Min Range: -4.6248
Max Act: 4.1560. Min Act: -0.1700
Data Index: 108767 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19