Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2814 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0274. Min Range: -8.0274
Max Act: 8.0274. Min Act: -0.1700
Data Index: 8615905 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0274. Min Range: -8.0274
Max Act: 7.9649. Min Act: -0.1700
Data Index: 6645088 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0274. Min Range: -8.0274
Max Act: 7.8399. Min Act: -0.1700
Data Index: 5875325 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0274. Min Range: -8.0274
Max Act: 7.8399. Min Act: -0.1700
Data Index: 1660911 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0274. Min Range: -8.0274
Max Act: 7.7149. Min Act: -0.1700
Data Index: 2599219 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0274. Min Range: -8.0274
Max Act: 7.6524. Min Act: -0.1700
Data Index: 2833660 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0274. Min Range: -8.0274
Max Act: 7.6524. Min Act: -0.1700
Data Index: 6349661 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0274. Min Range: -8.0274
Max Act: 7.6524. Min Act: -0.1700
Data Index: 4056805 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0274. Min Range: -8.0274
Max Act: 7.6524. Min Act: -0.1700
Data Index: 172026 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0274. Min Range: -8.0274
Max Act: 7.5899. Min Act: -0.1700
Data Index: 2855126 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0274. Min Range: -8.0274
Max Act: 7.5899. Min Act: -0.1700
Data Index: 3652386 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0274. Min Range: -8.0274
Max Act: 7.5274. Min Act: -0.1700
Data Index: 8272115 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0274. Min Range: -8.0274
Max Act: 7.5899. Min Act: -0.1700
Data Index: 5267759 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0274. Min Range: -8.0274
Max Act: 7.4649. Min Act: -0.1700
Data Index: 1852322 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0274. Min Range: -8.0274
Max Act: 7.4337. Min Act: -0.1700
Data Index: 3513554 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0274. Min Range: -8.0274
Max Act: 7.4649. Min Act: -0.1700
Data Index: 1807616 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0274. Min Range: -8.0274
Max Act: 7.4649. Min Act: -0.1700
Data Index: 5298120 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0274. Min Range: -8.0274
Max Act: 7.4024. Min Act: -0.1700
Data Index: 2251661 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0274. Min Range: -8.0274
Max Act: 7.4024. Min Act: -0.1700
Data Index: 720970 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0274. Min Range: -8.0274
Max Act: 7.4024. Min Act: -0.1700
Data Index: 5823601 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19