Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6036 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6604. Min Range: -5.6604
Max Act: 5.6604. Min Act: -0.1700
Data Index: 7399474 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6604. Min Range: -5.6604
Max Act: 5.4104. Min Act: -0.1700
Data Index: 3147867 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6604. Min Range: -5.6604
Max Act: 5.2229. Min Act: -0.1700
Data Index: 1087586 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6604. Min Range: -5.6604
Max Act: 5.1604. Min Act: -0.1700
Data Index: 1994682 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6604. Min Range: -5.6604
Max Act: 5.1291. Min Act: -0.1700
Data Index: 4850563 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6604. Min Range: -5.6604
Max Act: 5.0666. Min Act: -0.1700
Data Index: 6269933 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6604. Min Range: -5.6604
Max Act: 5.0979. Min Act: -0.1700
Data Index: 717319 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6604. Min Range: -5.6604
Max Act: 5.0666. Min Act: -0.1700
Data Index: 3922589 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6604. Min Range: -5.6604
Max Act: 5.0666. Min Act: -0.1700
Data Index: 8003213 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6604. Min Range: -5.6604
Max Act: 5.0354. Min Act: -0.1700
Data Index: 7764387 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6604. Min Range: -5.6604
Max Act: 5.0354. Min Act: -0.1700
Data Index: 3523355 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6604. Min Range: -5.6604
Max Act: 5.0354. Min Act: -0.1700
Data Index: 3523354 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6604. Min Range: -5.6604
Max Act: 5.0354. Min Act: -0.1700
Data Index: 2404313 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6604. Min Range: -5.6604
Max Act: 5.0354. Min Act: -0.1700
Data Index: 2080747 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6604. Min Range: -5.6604
Max Act: 5.0354. Min Act: -0.1700
Data Index: 7200159 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6604. Min Range: -5.6604
Max Act: 5.0041. Min Act: -0.1700
Data Index: 8245030 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6604. Min Range: -5.6604
Max Act: 4.9729. Min Act: -0.1700
Data Index: 1078004 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6604. Min Range: -5.6604
Max Act: 4.9729. Min Act: -0.1700
Data Index: 8007983 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6604. Min Range: -5.6604
Max Act: 4.9729. Min Act: -0.1700
Data Index: 821335 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6604. Min Range: -5.6604
Max Act: 4.9416. Min Act: -0.1700
Data Index: 5617900 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19