Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 30 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4207. Min Range: -5.4207
Max Act: 5.4207. Min Act: -0.1700
Data Index: 5697543 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4207. Min Range: -5.4207
Max Act: 5.2645. Min Act: -0.1700
Data Index: 7493934 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4207. Min Range: -5.4207
Max Act: 5.2645. Min Act: -0.1700
Data Index: 5326793 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4207. Min Range: -5.4207
Max Act: 5.2332. Min Act: -0.1700
Data Index: 5183684 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4207. Min Range: -5.4207
Max Act: 5.2332. Min Act: -0.1700
Data Index: 921167 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4207. Min Range: -5.4207
Max Act: 5.2020. Min Act: -0.1700
Data Index: 784505 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4207. Min Range: -5.4207
Max Act: 5.2020. Min Act: -0.1700
Data Index: 8151719 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4207. Min Range: -5.4207
Max Act: 5.2020. Min Act: -0.1700
Data Index: 5407205 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4207. Min Range: -5.4207
Max Act: 5.1707. Min Act: -0.1700
Data Index: 2956328 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4207. Min Range: -5.4207
Max Act: 5.1707. Min Act: -0.1700
Data Index: 8790465 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4207. Min Range: -5.4207
Max Act: 5.1707. Min Act: -0.1700
Data Index: 4943129 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4207. Min Range: -5.4207
Max Act: 5.2020. Min Act: -0.1700
Data Index: 6941680 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4207. Min Range: -5.4207
Max Act: 5.1707. Min Act: -0.1700
Data Index: 3271872 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4207. Min Range: -5.4207
Max Act: 5.1395. Min Act: -0.1700
Data Index: 6941670 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4207. Min Range: -5.4207
Max Act: 5.1395. Min Act: -0.1700
Data Index: 4645110 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4207. Min Range: -5.4207
Max Act: 5.1395. Min Act: -0.1700
Data Index: 7606875 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4207. Min Range: -5.4207
Max Act: 5.1707. Min Act: -0.1700
Data Index: 4863805 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4207. Min Range: -5.4207
Max Act: 5.1395. Min Act: -0.1700
Data Index: 5156981 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4207. Min Range: -5.4207
Max Act: 5.1082. Min Act: -0.1700
Data Index: 7363419 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4207. Min Range: -5.4207
Max Act: 5.0770. Min Act: -0.1700
Data Index: 3371258 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19