Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1598 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5109. Min Range: -6.5109
Max Act: 6.5109. Min Act: -0.1700
Data Index: 6944040 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5109. Min Range: -6.5109
Max Act: 6.4171. Min Act: -0.1700
Data Index: 3587273 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5109. Min Range: -6.5109
Max Act: 6.3859. Min Act: -0.1700
Data Index: 5653235 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5109. Min Range: -6.5109
Max Act: 6.3859. Min Act: -0.1700
Data Index: 4060922 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5109. Min Range: -6.5109
Max Act: 6.3546. Min Act: -0.1700
Data Index: 7302646 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5109. Min Range: -6.5109
Max Act: 6.3234. Min Act: -0.1700
Data Index: 1648392 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5109. Min Range: -6.5109
Max Act: 6.3234. Min Act: -0.1700
Data Index: 5659159 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5109. Min Range: -6.5109
Max Act: 6.2921. Min Act: -0.1700
Data Index: 6223160 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5109. Min Range: -6.5109
Max Act: 6.2609. Min Act: -0.1700
Data Index: 4324182 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5109. Min Range: -6.5109
Max Act: 6.2296. Min Act: -0.1700
Data Index: 1913758 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5109. Min Range: -6.5109
Max Act: 6.2296. Min Act: -0.1700
Data Index: 2124838 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5109. Min Range: -6.5109
Max Act: 6.1671. Min Act: -0.1700
Data Index: 3591796 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5109. Min Range: -6.5109
Max Act: 6.1671. Min Act: -0.1700
Data Index: 8498377 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5109. Min Range: -6.5109
Max Act: 6.1359. Min Act: -0.1700
Data Index: 487281 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5109. Min Range: -6.5109
Max Act: 6.1671. Min Act: -0.1700
Data Index: 5194265 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5109. Min Range: -6.5109
Max Act: 6.1671. Min Act: -0.1700
Data Index: 5172780 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5109. Min Range: -6.5109
Max Act: 6.1671. Min Act: -0.1700
Data Index: 4324183 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5109. Min Range: -6.5109
Max Act: 6.1671. Min Act: -0.1700
Data Index: 724177 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5109. Min Range: -6.5109
Max Act: 6.1671. Min Act: -0.1700
Data Index: 3607853 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5109. Min Range: -6.5109
Max Act: 6.1671. Min Act: -0.1700
Data Index: 861156 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19