Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2632 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1255. Min Range: -3.1255
Max Act: 3.1255. Min Act: -0.1700
Data Index: 1597990 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1255. Min Range: -3.1255
Max Act: 3.0625. Min Act: -0.1700
Data Index: 8460560 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1255. Min Range: -3.1255
Max Act: 3.0309. Min Act: -0.1700
Data Index: 1227389 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1255. Min Range: -3.1255
Max Act: 3.0309. Min Act: -0.1700
Data Index: 6735268 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1255. Min Range: -3.1255
Max Act: 2.9993. Min Act: -0.1700
Data Index: 4088596 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1255. Min Range: -3.1255
Max Act: 2.9835. Min Act: -0.1700
Data Index: 6661968 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1255. Min Range: -3.1255
Max Act: 2.9677. Min Act: -0.1700
Data Index: 1200825 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1255. Min Range: -3.1255
Max Act: 2.9677. Min Act: -0.1700
Data Index: 2667182 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1255. Min Range: -3.1255
Max Act: 2.9835. Min Act: -0.1700
Data Index: 3350475 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1255. Min Range: -3.1255
Max Act: 2.9519. Min Act: -0.1700
Data Index: 1718491 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1255. Min Range: -3.1255
Max Act: 2.9677. Min Act: -0.1700
Data Index: 6683225 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1255. Min Range: -3.1255
Max Act: 2.9519. Min Act: -0.1700
Data Index: 2301193 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1255. Min Range: -3.1255
Max Act: 2.9519. Min Act: -0.1700
Data Index: 7173195 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1255. Min Range: -3.1255
Max Act: 2.9519. Min Act: -0.1700
Data Index: 8425839 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1255. Min Range: -3.1255
Max Act: 2.9519. Min Act: -0.1700
Data Index: 8760126 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1255. Min Range: -3.1255
Max Act: 2.9202. Min Act: -0.1700
Data Index: 4778391 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1255. Min Range: -3.1255
Max Act: 2.9202. Min Act: -0.1700
Data Index: 5329925 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1255. Min Range: -3.1255
Max Act: 2.9519. Min Act: -0.1700
Data Index: 5481195 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1255. Min Range: -3.1255
Max Act: 2.9202. Min Act: -0.1700
Data Index: 465894 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1255. Min Range: -3.1255
Max Act: 2.9202. Min Act: -0.1700
Data Index: 2510819 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19