Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3008 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4961. Min Range: -7.4961
Max Act: 7.4961. Min Act: -0.1700
Data Index: 3438233 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4961. Min Range: -7.4961
Max Act: 7.1524. Min Act: -0.1700
Data Index: 2359389 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4961. Min Range: -7.4961
Max Act: 7.0274. Min Act: -0.1700
Data Index: 7384416 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4961. Min Range: -7.4961
Max Act: 6.9649. Min Act: -0.1700
Data Index: 4914466 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4961. Min Range: -7.4961
Max Act: 6.8711. Min Act: -0.1700
Data Index: 6558073 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4961. Min Range: -7.4961
Max Act: 6.8399. Min Act: -0.1700
Data Index: 2426677 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4961. Min Range: -7.4961
Max Act: 6.7461. Min Act: -0.1700
Data Index: 1221980 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4961. Min Range: -7.4961
Max Act: 6.7461. Min Act: -0.1700
Data Index: 5127104 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4961. Min Range: -7.4961
Max Act: 6.6836. Min Act: -0.1700
Data Index: 5858164 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4961. Min Range: -7.4961
Max Act: 6.7149. Min Act: -0.1700
Data Index: 86837 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4961. Min Range: -7.4961
Max Act: 6.6836. Min Act: -0.1700
Data Index: 812255 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4961. Min Range: -7.4961
Max Act: 6.6836. Min Act: -0.1700
Data Index: 6510035 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4961. Min Range: -7.4961
Max Act: 6.6524. Min Act: -0.1700
Data Index: 528684 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4961. Min Range: -7.4961
Max Act: 6.6211. Min Act: -0.1700
Data Index: 1242164 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4961. Min Range: -7.4961
Max Act: 6.6211. Min Act: -0.1700
Data Index: 4047499 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4961. Min Range: -7.4961
Max Act: 6.6211. Min Act: -0.1700
Data Index: 3802084 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4961. Min Range: -7.4961
Max Act: 6.5899. Min Act: -0.1700
Data Index: 1746447 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4961. Min Range: -7.4961
Max Act: 6.5899. Min Act: -0.1700
Data Index: 4237907 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4961. Min Range: -7.4961
Max Act: 6.5586. Min Act: -0.1700
Data Index: 6263470 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4961. Min Range: -7.4961
Max Act: 6.5899. Min Act: -0.1700
Data Index: 7005730 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19