Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 555 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.2515. Min Act: -0.1700
Data Index: 1829400 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.2202. Min Act: -0.1700
Data Index: 1632236 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.2202. Min Act: -0.1700
Data Index: 3746963 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.1890. Min Act: -0.1700
Data Index: 6006252 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.1890. Min Act: -0.1700
Data Index: 6387077 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.1577. Min Act: -0.1700
Data Index: 8494444 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.1577. Min Act: -0.1700
Data Index: 6705375 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.1264. Min Act: -0.1700
Data Index: 6155029 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.1577. Min Act: -0.1700
Data Index: 4447289 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.1577. Min Act: -0.1700
Data Index: 6512431 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.1264. Min Act: -0.1700
Data Index: 5046372 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.1577. Min Act: -0.1700
Data Index: 4476857 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.0952. Min Act: -0.1700
Data Index: 7210507 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.1264. Min Act: -0.1700
Data Index: 7612959 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.1264. Min Act: -0.1700
Data Index: 3065849 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.0952. Min Act: -0.1700
Data Index: 6598032 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.0952. Min Act: -0.1700
Data Index: 4613267 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.0639. Min Act: -0.1700
Data Index: 173475 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.0952. Min Act: -0.1700
Data Index: 7845884 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.0952. Min Act: -0.1700
Data Index: 8298149 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19