Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1941 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.7450. Min Act: -0.1700
Data Index: 6433537 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.5263. Min Act: -0.1700
Data Index: 838483 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.4950. Min Act: -0.1700
Data Index: 329504 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.4325. Min Act: -0.1700
Data Index: 6148557 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.4013. Min Act: -0.1700
Data Index: 8743718 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.2763. Min Act: -0.1700
Data Index: 4250748 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.2450. Min Act: -0.1700
Data Index: 8095608 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.2138. Min Act: -0.1700
Data Index: 1877781 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.1825. Min Act: -0.1700
Data Index: 6623777 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.1513. Min Act: -0.1700
Data Index: 5408178 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.1513. Min Act: -0.1700
Data Index: 8818035 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.1200. Min Act: -0.1700
Data Index: 4011143 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.0888. Min Act: -0.1700
Data Index: 4482622 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.0888. Min Act: -0.1700
Data Index: 1968718 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.0888. Min Act: -0.1700
Data Index: 5659289 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.0888. Min Act: -0.1700
Data Index: 926250 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.0575. Min Act: -0.1700
Data Index: 877944 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.0575. Min Act: -0.1700
Data Index: 7831799 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.0575. Min Act: -0.1700
Data Index: 227324 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7450. Min Range: -7.7450
Max Act: 7.0575. Min Act: -0.1700
Data Index: 8159074 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19