Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4718 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6575. Min Range: -5.6575
Max Act: 5.6575. Min Act: -0.1700
Data Index: 3669522 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6575. Min Range: -5.6575
Max Act: 5.6575. Min Act: -0.1700
Data Index: 1270073 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6575. Min Range: -5.6575
Max Act: 5.5950. Min Act: -0.1700
Data Index: 7961640 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6575. Min Range: -5.6575
Max Act: 5.4388. Min Act: -0.1700
Data Index: 8223023 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6575. Min Range: -5.6575
Max Act: 5.4075. Min Act: -0.1700
Data Index: 3932058 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6575. Min Range: -5.6575
Max Act: 5.4075. Min Act: -0.1700
Data Index: 7552297 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6575. Min Range: -5.6575
Max Act: 5.4075. Min Act: -0.1700
Data Index: 53685 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6575. Min Range: -5.6575
Max Act: 5.3763. Min Act: -0.1700
Data Index: 3165115 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6575. Min Range: -5.6575
Max Act: 5.3450. Min Act: -0.1700
Data Index: 3312645 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6575. Min Range: -5.6575
Max Act: 5.3138. Min Act: -0.1700
Data Index: 7685159 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6575. Min Range: -5.6575
Max Act: 5.3138. Min Act: -0.1700
Data Index: 1140280 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6575. Min Range: -5.6575
Max Act: 5.2513. Min Act: -0.1700
Data Index: 3669523 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6575. Min Range: -5.6575
Max Act: 5.2513. Min Act: -0.1700
Data Index: 396885 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6575. Min Range: -5.6575
Max Act: 5.2513. Min Act: -0.1700
Data Index: 8767403 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6575. Min Range: -5.6575
Max Act: 5.2513. Min Act: -0.1700
Data Index: 6473137 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6575. Min Range: -5.6575
Max Act: 5.2513. Min Act: -0.1700
Data Index: 4344038 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6575. Min Range: -5.6575
Max Act: 5.2513. Min Act: -0.1700
Data Index: 7054695 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6575. Min Range: -5.6575
Max Act: 5.2200. Min Act: -0.1700
Data Index: 5625965 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6575. Min Range: -5.6575
Max Act: 5.1888. Min Act: -0.1700
Data Index: 7972071 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6575. Min Range: -5.6575
Max Act: 5.1888. Min Act: -0.1700
Data Index: 2303453 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19