Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 118 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5042. Min Range: -5.5042
Max Act: 5.5042. Min Act: -0.1700
Data Index: 4702369 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5042. Min Range: -5.5042
Max Act: 5.2854. Min Act: -0.1700
Data Index: 8382374 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5042. Min Range: -5.5042
Max Act: 5.2854. Min Act: -0.1700
Data Index: 7397344 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5042. Min Range: -5.5042
Max Act: 5.2542. Min Act: -0.1700
Data Index: 1666582 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5042. Min Range: -5.5042
Max Act: 5.2229. Min Act: -0.1700
Data Index: 7821057 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5042. Min Range: -5.5042
Max Act: 5.1917. Min Act: -0.1700
Data Index: 313206 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5042. Min Range: -5.5042
Max Act: 5.1604. Min Act: -0.1700
Data Index: 2376867 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5042. Min Range: -5.5042
Max Act: 5.1604. Min Act: -0.1700
Data Index: 6562777 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5042. Min Range: -5.5042
Max Act: 5.1292. Min Act: -0.1700
Data Index: 3845598 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5042. Min Range: -5.5042
Max Act: 5.0667. Min Act: -0.1700
Data Index: 2360859 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5042. Min Range: -5.5042
Max Act: 5.0667. Min Act: -0.1700
Data Index: 5654210 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5042. Min Range: -5.5042
Max Act: 5.0979. Min Act: -0.1700
Data Index: 6169023 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5042. Min Range: -5.5042
Max Act: 5.0979. Min Act: -0.1700
Data Index: 3505621 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5042. Min Range: -5.5042
Max Act: 5.0979. Min Act: -0.1700
Data Index: 1669429 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5042. Min Range: -5.5042
Max Act: 5.0667. Min Act: -0.1700
Data Index: 3700648 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5042. Min Range: -5.5042
Max Act: 5.0354. Min Act: -0.1700
Data Index: 2302241 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5042. Min Range: -5.5042
Max Act: 5.0667. Min Act: -0.1700
Data Index: 1121804 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5042. Min Range: -5.5042
Max Act: 5.0667. Min Act: -0.1700
Data Index: 4598628 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5042. Min Range: -5.5042
Max Act: 5.0667. Min Act: -0.1700
Data Index: 1592449 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5042. Min Range: -5.5042
Max Act: 5.0354. Min Act: -0.1700
Data Index: 938728 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19