Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2947 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4437. Min Range: -9.4437
Max Act: 9.4437. Min Act: -0.1699
Data Index: 4897834 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4437. Min Range: -9.4437
Max Act: 9.0062. Min Act: -0.1700
Data Index: 4897835 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4437. Min Range: -9.4437
Max Act: 8.8812. Min Act: -0.1700
Data Index: 2867363 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4437. Min Range: -9.4437
Max Act: 8.8187. Min Act: -0.1699
Data Index: 5729 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4437. Min Range: -9.4437
Max Act: 8.6625. Min Act: -0.1700
Data Index: 145514 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4437. Min Range: -9.4437
Max Act: 8.6000. Min Act: -0.1700
Data Index: 4721692 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4437. Min Range: -9.4437
Max Act: 8.4437. Min Act: -0.1700
Data Index: 1797199 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4437. Min Range: -9.4437
Max Act: 8.3500. Min Act: -0.1700
Data Index: 1656723 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4437. Min Range: -9.4437
Max Act: 8.3500. Min Act: -0.1699
Data Index: 3206760 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4437. Min Range: -9.4437
Max Act: 8.3500. Min Act: -0.1700
Data Index: 8212328 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4437. Min Range: -9.4437
Max Act: 8.2250. Min Act: -0.1700
Data Index: 5417742 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4437. Min Range: -9.4437
Max Act: 8.1625. Min Act: -0.1700
Data Index: 7933238 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4437. Min Range: -9.4437
Max Act: 8.1625. Min Act: -0.1698
Data Index: 949366 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4437. Min Range: -9.4437
Max Act: 8.1000. Min Act: -0.1699
Data Index: 967544 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4437. Min Range: -9.4437
Max Act: 8.1000. Min Act: -0.1700
Data Index: 5730 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4437. Min Range: -9.4437
Max Act: 8.1000. Min Act: -0.1700
Data Index: 2146433 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4437. Min Range: -9.4437
Max Act: 8.1312. Min Act: -0.1700
Data Index: 1139517 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4437. Min Range: -9.4437
Max Act: 8.1000. Min Act: -0.1700
Data Index: 3158397 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4437. Min Range: -9.4437
Max Act: 8.1312. Min Act: -0.1700
Data Index: 4515911 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4437. Min Range: -9.4437
Max Act: 8.0687. Min Act: -0.1700
Data Index: 8495631 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19