Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2793. Min Range: -5.2793
Max Act: 5.2793. Min Act: -0.1700
Data Index: 6727379 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2793. Min Range: -5.2793
Max Act: 5.2168. Min Act: -0.1700
Data Index: 4901929 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2793. Min Range: -5.2793
Max Act: 5.1856. Min Act: -0.1700
Data Index: 6489414 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2793. Min Range: -5.2793
Max Act: 5.2168. Min Act: -0.1700
Data Index: 5685098 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2793. Min Range: -5.2793
Max Act: 5.1856. Min Act: -0.1700
Data Index: 1976892 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2793. Min Range: -5.2793
Max Act: 5.1231. Min Act: -0.1700
Data Index: 6343662 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2793. Min Range: -5.2793
Max Act: 5.1231. Min Act: -0.1700
Data Index: 1444195 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2793. Min Range: -5.2793
Max Act: 5.1543. Min Act: -0.1700
Data Index: 5253221 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2793. Min Range: -5.2793
Max Act: 5.0606. Min Act: -0.1700
Data Index: 2131490 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2793. Min Range: -5.2793
Max Act: 5.0606. Min Act: -0.1700
Data Index: 2672691 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2793. Min Range: -5.2793
Max Act: 5.0606. Min Act: -0.1700
Data Index: 6273434 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2793. Min Range: -5.2793
Max Act: 5.0606. Min Act: -0.1700
Data Index: 6624334 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2793. Min Range: -5.2793
Max Act: 5.0606. Min Act: -0.1700
Data Index: 5694519 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2793. Min Range: -5.2793
Max Act: 5.0293. Min Act: -0.1700
Data Index: 3634150 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2793. Min Range: -5.2793
Max Act: 5.0293. Min Act: -0.1700
Data Index: 1958519 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2793. Min Range: -5.2793
Max Act: 5.0293. Min Act: -0.1700
Data Index: 1017284 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2793. Min Range: -5.2793
Max Act: 5.0293. Min Act: -0.1700
Data Index: 4330901 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2793. Min Range: -5.2793
Max Act: 5.0293. Min Act: -0.1700
Data Index: 1563290 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2793. Min Range: -5.2793
Max Act: 4.9981. Min Act: -0.1700
Data Index: 2903407 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2793. Min Range: -5.2793
Max Act: 4.9981. Min Act: -0.1700
Data Index: 708250 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19