Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 284 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8350. Min Range: -3.8350
Max Act: 3.8350. Min Act: -0.1700
Data Index: 6045535 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8350. Min Range: -3.8350
Max Act: 3.8350. Min Act: -0.1700
Data Index: 8728626 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8350. Min Range: -3.8350
Max Act: 3.8350. Min Act: -0.1700
Data Index: 1715016 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8350. Min Range: -3.8350
Max Act: 3.6630. Min Act: -0.1700
Data Index: 4752524 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8350. Min Range: -3.8350
Max Act: 3.6160. Min Act: -0.1700
Data Index: 6090994 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8350. Min Range: -3.8350
Max Act: 3.6160. Min Act: -0.1700
Data Index: 5444944 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8350. Min Range: -3.8350
Max Act: 3.5847. Min Act: -0.1700
Data Index: 5244019 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8350. Min Range: -3.8350
Max Act: 3.5847. Min Act: -0.1700
Data Index: 2778400 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8350. Min Range: -3.8350
Max Act: 3.5691. Min Act: -0.1700
Data Index: 4077618 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8350. Min Range: -3.8350
Max Act: 3.5378. Min Act: -0.1700
Data Index: 713386 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8350. Min Range: -3.8350
Max Act: 3.5378. Min Act: -0.1700
Data Index: 2674184 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8350. Min Range: -3.8350
Max Act: 3.4908. Min Act: -0.1700
Data Index: 7776752 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8350. Min Range: -3.8350
Max Act: 3.5221. Min Act: -0.1700
Data Index: 40724 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8350. Min Range: -3.8350
Max Act: 3.5064. Min Act: -0.1700
Data Index: 2770137 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8350. Min Range: -3.8350
Max Act: 3.5064. Min Act: -0.1700
Data Index: 4534071 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8350. Min Range: -3.8350
Max Act: 3.5064. Min Act: -0.1700
Data Index: 4752523 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8350. Min Range: -3.8350
Max Act: 3.4751. Min Act: -0.1700
Data Index: 5760546 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8350. Min Range: -3.8350
Max Act: 3.4908. Min Act: -0.1700
Data Index: 4296969 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8350. Min Range: -3.8350
Max Act: 3.4908. Min Act: -0.1700
Data Index: 1189010 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8350. Min Range: -3.8350
Max Act: 3.4908. Min Act: -0.1700
Data Index: 423255 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19