Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3122 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.8059. Min Act: -0.1700
Data Index: 3089023 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.8059. Min Act: -0.1700
Data Index: 1234484 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.7747. Min Act: -0.1700
Data Index: 158053 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.8059. Min Act: -0.1700
Data Index: 4975708 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.7122. Min Act: -0.1700
Data Index: 2559796 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.5872. Min Act: -0.1700
Data Index: 8454083 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.5872. Min Act: -0.1700
Data Index: 6591361 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.5559. Min Act: -0.1700
Data Index: 3372764 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.5559. Min Act: -0.1700
Data Index: 7902510 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.5247. Min Act: -0.1700
Data Index: 7671327 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.5247. Min Act: -0.1700
Data Index: 4180775 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.5247. Min Act: -0.1700
Data Index: 2319937 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.4934. Min Act: -0.1700
Data Index: 1349868 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.4309. Min Act: -0.1700
Data Index: 5199465 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.4622. Min Act: -0.1700
Data Index: 4770498 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.4622. Min Act: -0.1700
Data Index: 7050404 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.3684. Min Act: -0.1700
Data Index: 4372822 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.3997. Min Act: -0.1700
Data Index: 1460460 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.3997. Min Act: -0.1700
Data Index: 422195 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.3684. Min Act: -0.1700
Data Index: 59419 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19