Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2246 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4059. Min Range: -4.4059
Max Act: 4.4059. Min Act: -0.1700
Data Index: 7598297 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4059. Min Range: -4.4059
Max Act: 4.1559. Min Act: -0.1700
Data Index: 3034922 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4059. Min Range: -4.4059
Max Act: 4.1246. Min Act: -0.1700
Data Index: 7947420 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4059. Min Range: -4.4059
Max Act: 4.0934. Min Act: -0.1700
Data Index: 1692068 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4059. Min Range: -4.4059
Max Act: 4.0934. Min Act: -0.1700
Data Index: 2832673 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4059. Min Range: -4.4059
Max Act: 4.0934. Min Act: -0.1700
Data Index: 5053958 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4059. Min Range: -4.4059
Max Act: 4.0621. Min Act: -0.1700
Data Index: 8291610 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4059. Min Range: -4.4059
Max Act: 4.0309. Min Act: -0.1700
Data Index: 5077870 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4059. Min Range: -4.4059
Max Act: 4.0309. Min Act: -0.1700
Data Index: 7146469 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4059. Min Range: -4.4059
Max Act: 3.9683. Min Act: -0.1700
Data Index: 1130913 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4059. Min Range: -4.4059
Max Act: 3.9683. Min Act: -0.1700
Data Index: 2054301 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4059. Min Range: -4.4059
Max Act: 3.9683. Min Act: -0.1700
Data Index: 5961067 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4059. Min Range: -4.4059
Max Act: 3.9683. Min Act: -0.1700
Data Index: 5184549 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4059. Min Range: -4.4059
Max Act: 3.9683. Min Act: -0.1700
Data Index: 7796120 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4059. Min Range: -4.4059
Max Act: 3.9371. Min Act: -0.1700
Data Index: 4768674 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4059. Min Range: -4.4059
Max Act: 3.9371. Min Act: -0.1700
Data Index: 4572937 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4059. Min Range: -4.4059
Max Act: 3.9371. Min Act: -0.1700
Data Index: 202048 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4059. Min Range: -4.4059
Max Act: 3.9371. Min Act: -0.1700
Data Index: 5401637 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4059. Min Range: -4.4059
Max Act: 3.9371. Min Act: -0.1700
Data Index: 8110817 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4059. Min Range: -4.4059
Max Act: 3.9683. Min Act: -0.1700
Data Index: 479552 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19