Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4031 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.4972. Min Act: -0.1700
Data Index: 8518825 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.4031. Min Act: -0.1700
Data Index: 4856774 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.3718. Min Act: -0.1700
Data Index: 4058054 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.3561. Min Act: -0.1700
Data Index: 6719862 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.3247. Min Act: -0.1700
Data Index: 862304 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.3404. Min Act: -0.1700
Data Index: 7338349 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.2619. Min Act: -0.1700
Data Index: 2145374 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.2776. Min Act: -0.1700
Data Index: 5725064 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.2462. Min Act: -0.1700
Data Index: 1083311 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.2619. Min Act: -0.1700
Data Index: 5832298 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.2462. Min Act: -0.1700
Data Index: 6982180 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.2462. Min Act: -0.1700
Data Index: 4398197 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.2462. Min Act: -0.1700
Data Index: 2672646 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.2305. Min Act: -0.1700
Data Index: 8334899 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.1990. Min Act: -0.1700
Data Index: 8611613 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.2148. Min Act: -0.1700
Data Index: 2789133 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.2148. Min Act: -0.1700
Data Index: 8330180 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.1676. Min Act: -0.1700
Data Index: 6713842 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.1833. Min Act: -0.1700
Data Index: 6037878 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.1833. Min Act: -0.1700
Data Index: 7338346 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19