Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1027 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8822. Min Range: -1.8822
Max Act: 1.8822. Min Act: -0.1700
Data Index: 312568 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8822. Min Range: -1.8822
Max Act: 1.8480. Min Act: -0.1700
Data Index: 6384858 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8822. Min Range: -1.8822
Max Act: 1.8223. Min Act: -0.1700
Data Index: 3351038 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8822. Min Range: -1.8822
Max Act: 1.8051. Min Act: -0.1700
Data Index: 3247563 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8822. Min Range: -1.8822
Max Act: 1.7534. Min Act: -0.1700
Data Index: 4018294 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8822. Min Range: -1.8822
Max Act: 1.7706. Min Act: -0.1700
Data Index: 6196552 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8822. Min Range: -1.8822
Max Act: 1.7534. Min Act: -0.1700
Data Index: 6848772 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8822. Min Range: -1.8822
Max Act: 1.7534. Min Act: -0.1700
Data Index: 8061801 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8822. Min Range: -1.8822
Max Act: 1.7361. Min Act: -0.1700
Data Index: 2166767 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8822. Min Range: -1.8822
Max Act: 1.7274. Min Act: -0.1700
Data Index: 48437 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8822. Min Range: -1.8822
Max Act: 1.7101. Min Act: -0.1700
Data Index: 2289811 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8822. Min Range: -1.8822
Max Act: 1.7361. Min Act: -0.1700
Data Index: 4906746 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8822. Min Range: -1.8822
Max Act: 1.6145. Min Act: -0.1697
Data Index: 8130987 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8822. Min Range: -1.8822
Max Act: 1.7101. Min Act: -0.1700
Data Index: 6021873 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8822. Min Range: -1.8822
Max Act: 1.7101. Min Act: -0.1700
Data Index: 4355656 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8822. Min Range: -1.8822
Max Act: 1.7101. Min Act: -0.1700
Data Index: 6848762 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8822. Min Range: -1.8822
Max Act: 1.7101. Min Act: -0.1700
Data Index: 506630 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8822. Min Range: -1.8822
Max Act: 1.6754. Min Act: -0.1700
Data Index: 5376228 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8822. Min Range: -1.8822
Max Act: 1.6841. Min Act: -0.1700
Data Index: 4867286 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8822. Min Range: -1.8822
Max Act: 1.6928. Min Act: -0.1700
Data Index: 6057927 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19