Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 940 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8274. Min Range: -6.8274
Max Act: 6.8274. Min Act: -0.1700
Data Index: 4463501 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8274. Min Range: -6.8274
Max Act: 6.5461. Min Act: -0.1700
Data Index: 1886835 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8274. Min Range: -6.8274
Max Act: 6.4836. Min Act: -0.1700
Data Index: 1206606 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8274. Min Range: -6.8274
Max Act: 6.4524. Min Act: -0.1700
Data Index: 2048975 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8274. Min Range: -6.8274
Max Act: 6.4524. Min Act: -0.1700
Data Index: 4222016 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8274. Min Range: -6.8274
Max Act: 6.3899. Min Act: -0.1700
Data Index: 1298027 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8274. Min Range: -6.8274
Max Act: 6.4524. Min Act: -0.1700
Data Index: 7451874 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8274. Min Range: -6.8274
Max Act: 6.4211. Min Act: -0.1700
Data Index: 4685492 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8274. Min Range: -6.8274
Max Act: 6.3899. Min Act: -0.1700
Data Index: 8443829 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8274. Min Range: -6.8274
Max Act: 6.3586. Min Act: -0.1700
Data Index: 4395730 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8274. Min Range: -6.8274
Max Act: 6.3899. Min Act: -0.1700
Data Index: 5390358 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8274. Min Range: -6.8274
Max Act: 6.3899. Min Act: -0.1700
Data Index: 5843201 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8274. Min Range: -6.8274
Max Act: 6.3899. Min Act: -0.1700
Data Index: 7740496 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8274. Min Range: -6.8274
Max Act: 6.3586. Min Act: -0.1700
Data Index: 2069985 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8274. Min Range: -6.8274
Max Act: 6.3586. Min Act: -0.1700
Data Index: 1882637 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8274. Min Range: -6.8274
Max Act: 6.3586. Min Act: -0.1700
Data Index: 7561513 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8274. Min Range: -6.8274
Max Act: 6.3586. Min Act: -0.1700
Data Index: 1108813 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8274. Min Range: -6.8274
Max Act: 6.2961. Min Act: -0.1700
Data Index: 2845718 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8274. Min Range: -6.8274
Max Act: 6.2961. Min Act: -0.1700
Data Index: 7440097 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8274. Min Range: -6.8274
Max Act: 6.2649. Min Act: -0.1700
Data Index: 7739930 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19