Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3162 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1784. Min Range: -4.1784
Max Act: 4.1784. Min Act: -0.1700
Data Index: 4243769 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1784. Min Range: -4.1784
Max Act: 4.1159. Min Act: -0.1700
Data Index: 7003232 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1784. Min Range: -4.1784
Max Act: 3.9596. Min Act: -0.1700
Data Index: 669616 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1784. Min Range: -4.1784
Max Act: 3.8971. Min Act: -0.1700
Data Index: 4238429 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1784. Min Range: -4.1784
Max Act: 3.8971. Min Act: -0.1700
Data Index: 10437 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1784. Min Range: -4.1784
Max Act: 3.8971. Min Act: -0.1700
Data Index: 575475 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1784. Min Range: -4.1784
Max Act: 3.8971. Min Act: -0.1700
Data Index: 3725766 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1784. Min Range: -4.1784
Max Act: 3.8658. Min Act: -0.1700
Data Index: 2211595 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1784. Min Range: -4.1784
Max Act: 3.8658. Min Act: -0.1700
Data Index: 8450042 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1784. Min Range: -4.1784
Max Act: 3.8502. Min Act: -0.1700
Data Index: 2392389 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1784. Min Range: -4.1784
Max Act: 3.7876. Min Act: -0.1700
Data Index: 6704469 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1784. Min Range: -4.1784
Max Act: 3.8033. Min Act: -0.1700
Data Index: 4379805 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1784. Min Range: -4.1784
Max Act: 3.7720. Min Act: -0.1700
Data Index: 3350722 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1784. Min Range: -4.1784
Max Act: 3.7720. Min Act: -0.1700
Data Index: 4089240 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1784. Min Range: -4.1784
Max Act: 3.7564. Min Act: -0.1700
Data Index: 178604 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1784. Min Range: -4.1784
Max Act: 3.7564. Min Act: -0.1700
Data Index: 3357833 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1784. Min Range: -4.1784
Max Act: 3.7564. Min Act: -0.1700
Data Index: 1913579 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1784. Min Range: -4.1784
Max Act: 3.7407. Min Act: -0.1700
Data Index: 70944 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1784. Min Range: -4.1784
Max Act: 3.7251. Min Act: -0.1700
Data Index: 4651753 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1784. Min Range: -4.1784
Max Act: 3.6938. Min Act: -0.1700
Data Index: 6327432 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #19