Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3030 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.2370. Min Act: -0.1700
Data Index: 5061110 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.2213. Min Act: -0.1700
Data Index: 3517639 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.1898. Min Act: -0.1700
Data Index: 6552204 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.1898. Min Act: -0.1700
Data Index: 5390372 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.1741. Min Act: -0.1700
Data Index: 4953918 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.1741. Min Act: -0.1700
Data Index: 2802474 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.1583. Min Act: -0.1700
Data Index: 4012683 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.1583. Min Act: -0.1700
Data Index: 5770582 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.1583. Min Act: -0.1700
Data Index: 5046731 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.1741. Min Act: -0.1700
Data Index: 3312796 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.1583. Min Act: -0.1700
Data Index: 7930406 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.1426. Min Act: -0.1700
Data Index: 4971264 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.1426. Min Act: -0.1700
Data Index: 4523429 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.1269. Min Act: -0.1700
Data Index: 571090 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.1426. Min Act: -0.1700
Data Index: 4639465 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.1111. Min Act: -0.1700
Data Index: 1495762 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.1111. Min Act: -0.1700
Data Index: 682832 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.1111. Min Act: -0.1700
Data Index: 5836026 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.1111. Min Act: -0.1700
Data Index: 5967107 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.1111. Min Act: -0.1700
Data Index: 6532496 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19