Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3089 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8816. Min Range: -6.8816
Max Act: 6.8816. Min Act: -0.1700
Data Index: 285092 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8816. Min Range: -6.8816
Max Act: 6.7566. Min Act: -0.1700
Data Index: 285099 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8816. Min Range: -6.8816
Max Act: 6.7566. Min Act: -0.1700
Data Index: 6940093 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8816. Min Range: -6.8816
Max Act: 6.7566. Min Act: -0.1699
Data Index: 1136108 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8816. Min Range: -6.8816
Max Act: 6.6628. Min Act: -0.1700
Data Index: 2278731 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8816. Min Range: -6.8816
Max Act: 6.6316. Min Act: -0.1700
Data Index: 285091 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8816. Min Range: -6.8816
Max Act: 6.5691. Min Act: -0.1700
Data Index: 505130 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8816. Min Range: -6.8816
Max Act: 6.5378. Min Act: -0.1700
Data Index: 6692943 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8816. Min Range: -6.8816
Max Act: 6.5378. Min Act: -0.1700
Data Index: 6145455 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8816. Min Range: -6.8816
Max Act: 6.4753. Min Act: -0.1700
Data Index: 2321466 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8816. Min Range: -6.8816
Max Act: 6.4753. Min Act: -0.1700
Data Index: 5908099 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8816. Min Range: -6.8816
Max Act: 6.4753. Min Act: -0.1700
Data Index: 3776511 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8816. Min Range: -6.8816
Max Act: 6.4753. Min Act: -0.1700
Data Index: 2733112 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8816. Min Range: -6.8816
Max Act: 6.4441. Min Act: -0.1700
Data Index: 101142 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8816. Min Range: -6.8816
Max Act: 6.4128. Min Act: -0.1700
Data Index: 6511481 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8816. Min Range: -6.8816
Max Act: 6.4128. Min Act: -0.1700
Data Index: 4777500 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8816. Min Range: -6.8816
Max Act: 6.4128. Min Act: -0.1700
Data Index: 1493433 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8816. Min Range: -6.8816
Max Act: 6.3816. Min Act: -0.1700
Data Index: 285098 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8816. Min Range: -6.8816
Max Act: 6.3503. Min Act: -0.1700
Data Index: 607672 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8816. Min Range: -6.8816
Max Act: 6.3816. Min Act: -0.1700
Data Index: 1493434 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19