Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5127 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3156. Min Range: -6.3156
Max Act: 6.3156. Min Act: -0.1700
Data Index: 5999255 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3156. Min Range: -6.3156
Max Act: 6.1281. Min Act: -0.1700
Data Index: 723407 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3156. Min Range: -6.3156
Max Act: 6.0031. Min Act: -0.1700
Data Index: 6489465 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3156. Min Range: -6.3156
Max Act: 5.9406. Min Act: -0.1700
Data Index: 1170608 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3156. Min Range: -6.3156
Max Act: 5.9406. Min Act: -0.1700
Data Index: 2728526 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3156. Min Range: -6.3156
Max Act: 5.9406. Min Act: -0.1700
Data Index: 3673974 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3156. Min Range: -6.3156
Max Act: 5.9093. Min Act: -0.1700
Data Index: 5724016 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3156. Min Range: -6.3156
Max Act: 5.8781. Min Act: -0.1700
Data Index: 7789942 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3156. Min Range: -6.3156
Max Act: 5.8781. Min Act: -0.1700
Data Index: 2585263 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3156. Min Range: -6.3156
Max Act: 5.8468. Min Act: -0.1700
Data Index: 2875072 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3156. Min Range: -6.3156
Max Act: 5.8468. Min Act: -0.1700
Data Index: 984660 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3156. Min Range: -6.3156
Max Act: 5.8156. Min Act: -0.1700
Data Index: 1652726 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3156. Min Range: -6.3156
Max Act: 5.8468. Min Act: -0.1700
Data Index: 5047078 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3156. Min Range: -6.3156
Max Act: 5.8156. Min Act: -0.1700
Data Index: 8098183 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3156. Min Range: -6.3156
Max Act: 5.8156. Min Act: -0.1700
Data Index: 4914677 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3156. Min Range: -6.3156
Max Act: 5.8156. Min Act: -0.1700
Data Index: 7318879 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3156. Min Range: -6.3156
Max Act: 5.8156. Min Act: -0.1700
Data Index: 3905307 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3156. Min Range: -6.3156
Max Act: 5.7843. Min Act: -0.1700
Data Index: 5199799 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3156. Min Range: -6.3156
Max Act: 5.7531. Min Act: -0.1700
Data Index: 676245 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3156. Min Range: -6.3156
Max Act: 5.7843. Min Act: -0.1700
Data Index: 5872344 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19