Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3175 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1023. Min Range: -6.1023
Max Act: 6.1023. Min Act: -0.1700
Data Index: 5200226 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1023. Min Range: -6.1023
Max Act: 5.9148. Min Act: -0.1700
Data Index: 8744936 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1023. Min Range: -6.1023
Max Act: 5.8835. Min Act: -0.1700
Data Index: 4141214 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1023. Min Range: -6.1023
Max Act: 5.8523. Min Act: -0.1700
Data Index: 8399831 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1023. Min Range: -6.1023
Max Act: 5.8523. Min Act: -0.1700
Data Index: 3502249 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1023. Min Range: -6.1023
Max Act: 5.7585. Min Act: -0.1700
Data Index: 5867829 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1023. Min Range: -6.1023
Max Act: 5.7585. Min Act: -0.1700
Data Index: 878123 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1023. Min Range: -6.1023
Max Act: 5.6960. Min Act: -0.1700
Data Index: 5422345 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1023. Min Range: -6.1023
Max Act: 5.7273. Min Act: -0.1700
Data Index: 5834000 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1023. Min Range: -6.1023
Max Act: 5.6335. Min Act: -0.1700
Data Index: 8326637 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1023. Min Range: -6.1023
Max Act: 5.6648. Min Act: -0.1700
Data Index: 6513659 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1023. Min Range: -6.1023
Max Act: 5.6648. Min Act: -0.1700
Data Index: 6788981 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1023. Min Range: -6.1023
Max Act: 5.6648. Min Act: -0.1700
Data Index: 719885 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1023. Min Range: -6.1023
Max Act: 5.6023. Min Act: -0.1700
Data Index: 5771687 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1023. Min Range: -6.1023
Max Act: 5.6023. Min Act: -0.1700
Data Index: 28456 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1023. Min Range: -6.1023
Max Act: 5.6023. Min Act: -0.1700
Data Index: 4334265 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1023. Min Range: -6.1023
Max Act: 5.6023. Min Act: -0.1700
Data Index: 639199 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1023. Min Range: -6.1023
Max Act: 5.6023. Min Act: -0.1700
Data Index: 1918086 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1023. Min Range: -6.1023
Max Act: 5.5710. Min Act: -0.1700
Data Index: 5321393 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1023. Min Range: -6.1023
Max Act: 5.5710. Min Act: -0.1700
Data Index: 7843857 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19