Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2267 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4978. Min Range: -3.4978
Max Act: 3.4978. Min Act: -0.1700
Data Index: 7014210 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4978. Min Range: -3.4978
Max Act: 3.2783. Min Act: -0.1700
Data Index: 6887006 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4978. Min Range: -3.4978
Max Act: 3.2626. Min Act: -0.1700
Data Index: 7727269 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4978. Min Range: -3.4978
Max Act: 3.2469. Min Act: -0.1700
Data Index: 1937350 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4978. Min Range: -3.4978
Max Act: 3.2154. Min Act: -0.1700
Data Index: 2998949 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4978. Min Range: -3.4978
Max Act: 3.2154. Min Act: -0.1700
Data Index: 7172027 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4978. Min Range: -3.4978
Max Act: 3.1997. Min Act: -0.1700
Data Index: 899148 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4978. Min Range: -3.4978
Max Act: 3.1840. Min Act: -0.1700
Data Index: 2369513 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4978. Min Range: -3.4978
Max Act: 3.1840. Min Act: -0.1700
Data Index: 124040 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4978. Min Range: -3.4978
Max Act: 3.1683. Min Act: -0.1700
Data Index: 1097681 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4978. Min Range: -3.4978
Max Act: 3.1840. Min Act: -0.1700
Data Index: 6967675 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4978. Min Range: -3.4978
Max Act: 3.1840. Min Act: -0.1700
Data Index: 1097682 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4978. Min Range: -3.4978
Max Act: 3.1525. Min Act: -0.1700
Data Index: 2163885 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4978. Min Range: -3.4978
Max Act: 3.1368. Min Act: -0.1700
Data Index: 6505455 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4978. Min Range: -3.4978
Max Act: 3.1525. Min Act: -0.1700
Data Index: 8656773 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4978. Min Range: -3.4978
Max Act: 3.1210. Min Act: -0.1700
Data Index: 559702 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4978. Min Range: -3.4978
Max Act: 3.1525. Min Act: -0.1700
Data Index: 8659453 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4978. Min Range: -3.4978
Max Act: 3.1210. Min Act: -0.1700
Data Index: 7202791 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4978. Min Range: -3.4978
Max Act: 3.1053. Min Act: -0.1700
Data Index: 7426604 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4978. Min Range: -3.4978
Max Act: 3.1368. Min Act: -0.1700
Data Index: 3249495 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19