Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2917 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0772. Min Range: -7.0772
Max Act: 7.0772. Min Act: -0.1700
Data Index: 3416593 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0772. Min Range: -7.0772
Max Act: 7.0459. Min Act: -0.1700
Data Index: 1574142 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0772. Min Range: -7.0772
Max Act: 7.0147. Min Act: -0.1700
Data Index: 3872228 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0772. Min Range: -7.0772
Max Act: 6.9834. Min Act: -0.1700
Data Index: 3762977 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0772. Min Range: -7.0772
Max Act: 6.9209. Min Act: -0.1700
Data Index: 8643369 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0772. Min Range: -7.0772
Max Act: 6.8897. Min Act: -0.1700
Data Index: 1383730 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0772. Min Range: -7.0772
Max Act: 6.8584. Min Act: -0.1700
Data Index: 7169168 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0772. Min Range: -7.0772
Max Act: 6.8897. Min Act: -0.1700
Data Index: 7312102 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0772. Min Range: -7.0772
Max Act: 6.8584. Min Act: -0.1700
Data Index: 1438066 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0772. Min Range: -7.0772
Max Act: 6.8584. Min Act: -0.1700
Data Index: 4397738 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0772. Min Range: -7.0772
Max Act: 6.8272. Min Act: -0.1700
Data Index: 7665162 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0772. Min Range: -7.0772
Max Act: 6.7959. Min Act: -0.1700
Data Index: 1460015 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0772. Min Range: -7.0772
Max Act: 6.7959. Min Act: -0.1700
Data Index: 5631071 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0772. Min Range: -7.0772
Max Act: 6.7959. Min Act: -0.1700
Data Index: 8735882 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0772. Min Range: -7.0772
Max Act: 6.7959. Min Act: -0.1700
Data Index: 703149 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0772. Min Range: -7.0772
Max Act: 6.7647. Min Act: -0.1700
Data Index: 7794334 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0772. Min Range: -7.0772
Max Act: 6.7959. Min Act: -0.1700
Data Index: 8410673 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0772. Min Range: -7.0772
Max Act: 6.7334. Min Act: -0.1700
Data Index: 6120145 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0772. Min Range: -7.0772
Max Act: 6.7334. Min Act: -0.1700
Data Index: 6375189 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0772. Min Range: -7.0772
Max Act: 6.7334. Min Act: -0.1700
Data Index: 2000891 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19