Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2301 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2445. Min Range: -6.2445
Max Act: 6.2445. Min Act: -0.1700
Data Index: 4516010 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2445. Min Range: -6.2445
Max Act: 5.9945. Min Act: -0.1700
Data Index: 5167599 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2445. Min Range: -6.2445
Max Act: 5.9633. Min Act: -0.1700
Data Index: 1421791 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2445. Min Range: -6.2445
Max Act: 5.9320. Min Act: -0.1700
Data Index: 6782116 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2445. Min Range: -6.2445
Max Act: 5.8695. Min Act: -0.1700
Data Index: 8233805 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2445. Min Range: -6.2445
Max Act: 5.8695. Min Act: -0.1700
Data Index: 8291737 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2445. Min Range: -6.2445
Max Act: 5.8695. Min Act: -0.1700
Data Index: 8233821 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2445. Min Range: -6.2445
Max Act: 5.8695. Min Act: -0.1700
Data Index: 3015491 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2445. Min Range: -6.2445
Max Act: 5.7758. Min Act: -0.1700
Data Index: 8551120 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2445. Min Range: -6.2445
Max Act: 5.7133. Min Act: -0.1700
Data Index: 4474064 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2445. Min Range: -6.2445
Max Act: 5.6820. Min Act: -0.1700
Data Index: 120366 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2445. Min Range: -6.2445
Max Act: 5.6820. Min Act: -0.1700
Data Index: 1622719 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2445. Min Range: -6.2445
Max Act: 5.7133. Min Act: -0.1700
Data Index: 8540470 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2445. Min Range: -6.2445
Max Act: 5.6508. Min Act: -0.1700
Data Index: 2213441 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2445. Min Range: -6.2445
Max Act: 5.6195. Min Act: -0.1700
Data Index: 4228402 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2445. Min Range: -6.2445
Max Act: 5.6195. Min Act: -0.1700
Data Index: 3346816 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2445. Min Range: -6.2445
Max Act: 5.6508. Min Act: -0.1700
Data Index: 8235710 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2445. Min Range: -6.2445
Max Act: 5.6195. Min Act: -0.1700
Data Index: 7718078 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2445. Min Range: -6.2445
Max Act: 5.6195. Min Act: -0.1700
Data Index: 1722313 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2445. Min Range: -6.2445
Max Act: 5.5883. Min Act: -0.1700
Data Index: 8233809 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19