Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5857 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8611. Min Range: -5.8611
Max Act: 5.8611. Min Act: -0.1700
Data Index: 7331870 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8611. Min Range: -5.8611
Max Act: 5.8611. Min Act: -0.1700
Data Index: 1803537 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8611. Min Range: -5.8611
Max Act: 5.7986. Min Act: -0.1700
Data Index: 405244 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8611. Min Range: -5.8611
Max Act: 5.7673. Min Act: -0.1700
Data Index: 4913977 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8611. Min Range: -5.8611
Max Act: 5.7673. Min Act: -0.1700
Data Index: 8215372 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8611. Min Range: -5.8611
Max Act: 5.7673. Min Act: -0.1700
Data Index: 988224 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8611. Min Range: -5.8611
Max Act: 5.7673. Min Act: -0.1700
Data Index: 1335445 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8611. Min Range: -5.8611
Max Act: 5.7673. Min Act: -0.1700
Data Index: 7244882 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8611. Min Range: -5.8611
Max Act: 5.7673. Min Act: -0.1700
Data Index: 5215451 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8611. Min Range: -5.8611
Max Act: 5.7361. Min Act: -0.1700
Data Index: 6954409 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8611. Min Range: -5.8611
Max Act: 5.7361. Min Act: -0.1700
Data Index: 6762095 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8611. Min Range: -5.8611
Max Act: 5.7361. Min Act: -0.1700
Data Index: 6371869 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8611. Min Range: -5.8611
Max Act: 5.7361. Min Act: -0.1700
Data Index: 145184 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8611. Min Range: -5.8611
Max Act: 5.7361. Min Act: -0.1700
Data Index: 3021480 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8611. Min Range: -5.8611
Max Act: 5.7048. Min Act: -0.1700
Data Index: 4217366 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8611. Min Range: -5.8611
Max Act: 5.7048. Min Act: -0.1700
Data Index: 5951051 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8611. Min Range: -5.8611
Max Act: 5.7048. Min Act: -0.1700
Data Index: 5216255 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8611. Min Range: -5.8611
Max Act: 5.7048. Min Act: -0.1700
Data Index: 5015298 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8611. Min Range: -5.8611
Max Act: 5.7048. Min Act: -0.1700
Data Index: 5083575 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8611. Min Range: -5.8611
Max Act: 5.6736. Min Act: -0.1700
Data Index: 2293683 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19