Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 154 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0406. Min Range: -5.0406
Max Act: 5.0406. Min Act: -0.1700
Data Index: 3746349 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.8843. Min Act: -0.1700
Data Index: 1527948 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.9156. Min Act: -0.1700
Data Index: 7052245 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.8531. Min Act: -0.1700
Data Index: 4226038 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.8218. Min Act: -0.1700
Data Index: 3065709 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.8218. Min Act: -0.1700
Data Index: 3538812 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.7906. Min Act: -0.1700
Data Index: 6472758 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.7593. Min Act: -0.1700
Data Index: 2349593 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.7593. Min Act: -0.1700
Data Index: 6400557 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.7906. Min Act: -0.1700
Data Index: 953603 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.7281. Min Act: -0.1700
Data Index: 3303522 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.7281. Min Act: -0.1700
Data Index: 1097724 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.7281. Min Act: -0.1700
Data Index: 5536312 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.6968. Min Act: -0.1700
Data Index: 1283003 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.6968. Min Act: -0.1700
Data Index: 7903912 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.6656. Min Act: -0.1700
Data Index: 5744248 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.6968. Min Act: -0.1700
Data Index: 4546238 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.6968. Min Act: -0.1700
Data Index: 2087747 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.6968. Min Act: -0.1700
Data Index: 3476718 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0406. Min Range: -5.0406
Max Act: 4.6968. Min Act: -0.1700
Data Index: 4333508 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19