Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3289 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8704. Min Range: -7.8704
Max Act: 7.8704. Min Act: -0.1700
Data Index: 6219478 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8704. Min Range: -7.8704
Max Act: 7.5267. Min Act: -0.1700
Data Index: 6302441 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8704. Min Range: -7.8704
Max Act: 7.5267. Min Act: -0.1700
Data Index: 2404146 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8704. Min Range: -7.8704
Max Act: 7.4642. Min Act: -0.1700
Data Index: 5584753 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8704. Min Range: -7.8704
Max Act: 7.4017. Min Act: -0.1700
Data Index: 8442940 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8704. Min Range: -7.8704
Max Act: 7.2767. Min Act: -0.1700
Data Index: 1190722 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8704. Min Range: -7.8704
Max Act: 7.2454. Min Act: -0.1700
Data Index: 3991853 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8704. Min Range: -7.8704
Max Act: 7.2767. Min Act: -0.1700
Data Index: 1303109 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8704. Min Range: -7.8704
Max Act: 7.2142. Min Act: -0.1700
Data Index: 1365482 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8704. Min Range: -7.8704
Max Act: 7.2142. Min Act: -0.1700
Data Index: 1407756 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8704. Min Range: -7.8704
Max Act: 7.1204. Min Act: -0.1700
Data Index: 391963 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8704. Min Range: -7.8704
Max Act: 7.1517. Min Act: -0.1700
Data Index: 6425787 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8704. Min Range: -7.8704
Max Act: 7.1204. Min Act: -0.1700
Data Index: 4374332 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8704. Min Range: -7.8704
Max Act: 7.1204. Min Act: -0.1700
Data Index: 8118442 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8704. Min Range: -7.8704
Max Act: 7.1204. Min Act: -0.1700
Data Index: 1651001 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8704. Min Range: -7.8704
Max Act: 7.1204. Min Act: -0.1700
Data Index: 29035 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8704. Min Range: -7.8704
Max Act: 7.0892. Min Act: -0.1700
Data Index: 4123850 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8704. Min Range: -7.8704
Max Act: 7.0892. Min Act: -0.1700
Data Index: 4991517 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8704. Min Range: -7.8704
Max Act: 7.0892. Min Act: -0.1700
Data Index: 491887 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8704. Min Range: -7.8704
Max Act: 7.0579. Min Act: -0.1700
Data Index: 3939582 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19