Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2350 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.2682. Min Range: -1.2682
Max Act: 1.2682. Min Act: -0.1700
Data Index: 8438518 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2682. Min Range: -1.2682
Max Act: 1.1099. Min Act: -0.1689
Data Index: 5620254 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2682. Min Range: -1.2682
Max Act: 1.0749. Min Act: -0.1675
Data Index: 5114341 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2682. Min Range: -1.2682
Max Act: 1.0400. Min Act: -0.1700
Data Index: 1556742 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2682. Min Range: -1.2682
Max Act: 1.0225. Min Act: -0.1700
Data Index: 3930588 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2682. Min Range: -1.2682
Max Act: 1.0225. Min Act: -0.1690
Data Index: 8704169 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2682. Min Range: -1.2682
Max Act: 1.0225. Min Act: -0.1700
Data Index: 2107960 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2682. Min Range: -1.2682
Max Act: 1.0052. Min Act: -0.1686
Data Index: 5337184 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2682. Min Range: -1.2682
Max Act: 0.9878. Min Act: -0.1691
Data Index: 611410 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2682. Min Range: -1.2682
Max Act: 0.9878. Min Act: -0.1699
Data Index: 8749211 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2682. Min Range: -1.2682
Max Act: 0.9878. Min Act: -0.1694
Data Index: 5504303 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2682. Min Range: -1.2682
Max Act: 0.9705. Min Act: -0.1700
Data Index: 4471599 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2682. Min Range: -1.2682
Max Act: 0.9532. Min Act: -0.1643
Data Index: 6864924 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2682. Min Range: -1.2682
Max Act: 0.9705. Min Act: -0.1700
Data Index: 2544065 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2682. Min Range: -1.2682
Max Act: 0.9532. Min Act: -0.1700
Data Index: 3947538 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2682. Min Range: -1.2682
Max Act: 0.9532. Min Act: -0.1700
Data Index: 6612896 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2682. Min Range: -1.2682
Max Act: 0.9360. Min Act: -0.1700
Data Index: 2791403 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2682. Min Range: -1.2682
Max Act: 0.9360. Min Act: -0.1663
Data Index: 6608984 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2682. Min Range: -1.2682
Max Act: 0.9360. Min Act: -0.1696
Data Index: 430557 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2682. Min Range: -1.2682
Max Act: 0.9532. Min Act: -0.1687
Data Index: 157232 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19