Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5424 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6577. Min Range: -9.6577
Max Act: 9.6577. Min Act: -0.1700
Data Index: 8319381 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6577. Min Range: -9.6577
Max Act: 9.5327. Min Act: -0.1700
Data Index: 1076977 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6577. Min Range: -9.6577
Max Act: 9.4702. Min Act: -0.1700
Data Index: 7306595 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6577. Min Range: -9.6577
Max Act: 9.4077. Min Act: -0.1700
Data Index: 4694193 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6577. Min Range: -9.6577
Max Act: 9.4077. Min Act: -0.1700
Data Index: 6110790 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6577. Min Range: -9.6577
Max Act: 9.4077. Min Act: -0.1700
Data Index: 7771575 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6577. Min Range: -9.6577
Max Act: 9.4077. Min Act: -0.1700
Data Index: 4621843 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6577. Min Range: -9.6577
Max Act: 9.4077. Min Act: -0.1700
Data Index: 8375759 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6577. Min Range: -9.6577
Max Act: 9.4077. Min Act: -0.1700
Data Index: 8319094 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6577. Min Range: -9.6577
Max Act: 9.3452. Min Act: -0.1700
Data Index: 7670995 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6577. Min Range: -9.6577
Max Act: 9.3452. Min Act: -0.1700
Data Index: 6568530 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6577. Min Range: -9.6577
Max Act: 9.3452. Min Act: -0.1700
Data Index: 6387493 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6577. Min Range: -9.6577
Max Act: 9.3452. Min Act: -0.1700
Data Index: 6226374 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6577. Min Range: -9.6577
Max Act: 9.3452. Min Act: -0.1700
Data Index: 5102876 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6577. Min Range: -9.6577
Max Act: 9.2827. Min Act: -0.1700
Data Index: 787748 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6577. Min Range: -9.6577
Max Act: 9.2827. Min Act: -0.1700
Data Index: 6705946 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6577. Min Range: -9.6577
Max Act: 9.2827. Min Act: -0.1700
Data Index: 4520314 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6577. Min Range: -9.6577
Max Act: 9.2827. Min Act: -0.1700
Data Index: 890077 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6577. Min Range: -9.6577
Max Act: 9.2202. Min Act: -0.1700
Data Index: 4349511 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6577. Min Range: -9.6577
Max Act: 9.2827. Min Act: -0.1700
Data Index: 6174265 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19