Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4248 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6485. Min Range: -4.6485
Max Act: 4.6485. Min Act: -0.1697
Data Index: 6726667 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6485. Min Range: -4.6485
Max Act: 4.5235. Min Act: -0.1699
Data Index: 3659522 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6485. Min Range: -4.6485
Max Act: 4.4297. Min Act: -0.1700
Data Index: 7611910 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6485. Min Range: -4.6485
Max Act: 4.2735. Min Act: -0.1699
Data Index: 18353 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6485. Min Range: -4.6485
Max Act: 4.2735. Min Act: -0.1678
Data Index: 4570392 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6485. Min Range: -4.6485
Max Act: 4.2735. Min Act: -0.1684
Data Index: 328109 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6485. Min Range: -4.6485
Max Act: 4.2735. Min Act: -0.1678
Data Index: 4449746 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6485. Min Range: -4.6485
Max Act: 4.2735. Min Act: -0.1695
Data Index: 5243602 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6485. Min Range: -4.6485
Max Act: 4.2735. Min Act: -0.1683
Data Index: 4843307 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6485. Min Range: -4.6485
Max Act: 4.2422. Min Act: -0.1697
Data Index: 2643595 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6485. Min Range: -4.6485
Max Act: 4.2110. Min Act: -0.1693
Data Index: 7601150 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6485. Min Range: -4.6485
Max Act: 4.2110. Min Act: -0.1697
Data Index: 1011770 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6485. Min Range: -4.6485
Max Act: 4.1797. Min Act: -0.1678
Data Index: 7296102 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6485. Min Range: -4.6485
Max Act: 4.1797. Min Act: -0.1678
Data Index: 7493502 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6485. Min Range: -4.6485
Max Act: 4.1484. Min Act: -0.1678
Data Index: 2824049 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6485. Min Range: -4.6485
Max Act: 4.1484. Min Act: -0.1678
Data Index: 1860311 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6485. Min Range: -4.6485
Max Act: 4.0859. Min Act: -0.1682
Data Index: 3315999 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6485. Min Range: -4.6485
Max Act: 4.0547. Min Act: -0.1678
Data Index: 7949018 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6485. Min Range: -4.6485
Max Act: 4.0234. Min Act: -0.1678
Data Index: 388090 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6485. Min Range: -4.6485
Max Act: 4.0234. Min Act: -0.1678
Data Index: 849479 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19