Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3296 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5639. Min Range: -4.5639
Max Act: 4.5639. Min Act: -0.1700
Data Index: 4480740 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5639. Min Range: -4.5639
Max Act: 4.5639. Min Act: -0.1700
Data Index: 6955054 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5639. Min Range: -4.5639
Max Act: 4.5014. Min Act: -0.1700
Data Index: 2600200 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5639. Min Range: -4.5639
Max Act: 4.4389. Min Act: -0.1700
Data Index: 7889142 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5639. Min Range: -4.5639
Max Act: 4.4389. Min Act: -0.1700
Data Index: 8312235 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5639. Min Range: -4.5639
Max Act: 4.4077. Min Act: -0.1700
Data Index: 8114119 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5639. Min Range: -4.5639
Max Act: 4.3764. Min Act: -0.1700
Data Index: 3100700 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5639. Min Range: -4.5639
Max Act: 4.3452. Min Act: -0.1700
Data Index: 8262365 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5639. Min Range: -4.5639
Max Act: 4.3139. Min Act: -0.1700
Data Index: 4276516 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5639. Min Range: -4.5639
Max Act: 4.3139. Min Act: -0.1700
Data Index: 8035107 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5639. Min Range: -4.5639
Max Act: 4.2827. Min Act: -0.1700
Data Index: 7479085 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5639. Min Range: -4.5639
Max Act: 4.2827. Min Act: -0.1700
Data Index: 4095228 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5639. Min Range: -4.5639
Max Act: 4.2514. Min Act: -0.1700
Data Index: 3326230 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5639. Min Range: -4.5639
Max Act: 4.2202. Min Act: -0.1700
Data Index: 6792728 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5639. Min Range: -4.5639
Max Act: 4.2202. Min Act: -0.1700
Data Index: 1544591 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5639. Min Range: -4.5639
Max Act: 4.1889. Min Act: -0.1700
Data Index: 7716000 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5639. Min Range: -4.5639
Max Act: 4.1577. Min Act: -0.1700
Data Index: 2584969 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5639. Min Range: -4.5639
Max Act: 4.1577. Min Act: -0.1700
Data Index: 6659627 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5639. Min Range: -4.5639
Max Act: 4.1577. Min Act: -0.1700
Data Index: 4523826 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5639. Min Range: -4.5639
Max Act: 4.1264. Min Act: -0.1700
Data Index: 3214809 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19