Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 439 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0190. Min Range: -4.0190
Max Act: 4.0190. Min Act: -0.1700
Data Index: 6354252 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0190. Min Range: -4.0190
Max Act: 3.9877. Min Act: -0.1700
Data Index: 7504409 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0190. Min Range: -4.0190
Max Act: 3.8940. Min Act: -0.1700
Data Index: 3828148 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0190. Min Range: -4.0190
Max Act: 3.9252. Min Act: -0.1700
Data Index: 2644471 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0190. Min Range: -4.0190
Max Act: 3.8627. Min Act: -0.1700
Data Index: 1655345 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0190. Min Range: -4.0190
Max Act: 3.8940. Min Act: -0.1700
Data Index: 8321 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0190. Min Range: -4.0190
Max Act: 3.8627. Min Act: -0.1700
Data Index: 3987289 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0190. Min Range: -4.0190
Max Act: 3.8627. Min Act: -0.1700
Data Index: 5144211 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0190. Min Range: -4.0190
Max Act: 3.8627. Min Act: -0.1700
Data Index: 1080618 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0190. Min Range: -4.0190
Max Act: 3.8314. Min Act: -0.1700
Data Index: 106614 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0190. Min Range: -4.0190
Max Act: 3.8001. Min Act: -0.1700
Data Index: 4593640 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0190. Min Range: -4.0190
Max Act: 3.8001. Min Act: -0.1700
Data Index: 1234500 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0190. Min Range: -4.0190
Max Act: 3.8001. Min Act: -0.1700
Data Index: 3335545 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0190. Min Range: -4.0190
Max Act: 3.7689. Min Act: -0.1700
Data Index: 3520336 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0190. Min Range: -4.0190
Max Act: 3.7689. Min Act: -0.1700
Data Index: 8405049 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0190. Min Range: -4.0190
Max Act: 3.8001. Min Act: -0.1700
Data Index: 2658906 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0190. Min Range: -4.0190
Max Act: 3.7689. Min Act: -0.1700
Data Index: 8031367 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0190. Min Range: -4.0190
Max Act: 3.7376. Min Act: -0.1700
Data Index: 1934452 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0190. Min Range: -4.0190
Max Act: 3.7376. Min Act: -0.1700
Data Index: 5548839 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0190. Min Range: -4.0190
Max Act: 3.7376. Min Act: -0.1700
Data Index: 5766780 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #19