Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2618 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9490. Min Range: -7.9490
Max Act: 7.9490. Min Act: -0.1700
Data Index: 8769008 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9490. Min Range: -7.9490
Max Act: 7.3240. Min Act: -0.1700
Data Index: 2474624 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9490. Min Range: -7.9490
Max Act: 7.1990. Min Act: -0.1700
Data Index: 3695768 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9490. Min Range: -7.9490
Max Act: 7.1677. Min Act: -0.1700
Data Index: 2016019 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9490. Min Range: -7.9490
Max Act: 7.0427. Min Act: -0.1700
Data Index: 8270922 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9490. Min Range: -7.9490
Max Act: 7.0115. Min Act: -0.1700
Data Index: 5116861 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9490. Min Range: -7.9490
Max Act: 6.9802. Min Act: -0.1700
Data Index: 7035510 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9490. Min Range: -7.9490
Max Act: 6.9490. Min Act: -0.1700
Data Index: 884918 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9490. Min Range: -7.9490
Max Act: 6.9177. Min Act: -0.1700
Data Index: 7497124 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9490. Min Range: -7.9490
Max Act: 6.8865. Min Act: -0.1700
Data Index: 1158944 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9490. Min Range: -7.9490
Max Act: 6.8865. Min Act: -0.1700
Data Index: 6531912 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9490. Min Range: -7.9490
Max Act: 6.8865. Min Act: -0.1700
Data Index: 2685458 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9490. Min Range: -7.9490
Max Act: 6.8865. Min Act: -0.1700
Data Index: 8807208 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9490. Min Range: -7.9490
Max Act: 6.8865. Min Act: -0.1700
Data Index: 910149 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9490. Min Range: -7.9490
Max Act: 6.8552. Min Act: -0.1700
Data Index: 3094140 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9490. Min Range: -7.9490
Max Act: 6.7615. Min Act: -0.1700
Data Index: 4145730 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9490. Min Range: -7.9490
Max Act: 6.7927. Min Act: -0.1700
Data Index: 697067 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9490. Min Range: -7.9490
Max Act: 6.7927. Min Act: -0.1700
Data Index: 729219 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9490. Min Range: -7.9490
Max Act: 6.7615. Min Act: -0.1700
Data Index: 7894706 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9490. Min Range: -7.9490
Max Act: 6.7615. Min Act: -0.1700
Data Index: 460100 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19