Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1684 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0529. Min Range: -6.0529
Max Act: 6.0529. Min Act: -0.1700
Data Index: 3535357 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0529. Min Range: -6.0529
Max Act: 5.9904. Min Act: -0.1700
Data Index: 110094 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0529. Min Range: -6.0529
Max Act: 5.9279. Min Act: -0.1700
Data Index: 3199219 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0529. Min Range: -6.0529
Max Act: 5.9591. Min Act: -0.1700
Data Index: 3910595 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0529. Min Range: -6.0529
Max Act: 5.9591. Min Act: -0.1700
Data Index: 3644196 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0529. Min Range: -6.0529
Max Act: 5.9591. Min Act: -0.1700
Data Index: 3863323 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0529. Min Range: -6.0529
Max Act: 5.9591. Min Act: -0.1700
Data Index: 6782221 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0529. Min Range: -6.0529
Max Act: 5.9279. Min Act: -0.1700
Data Index: 6772835 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0529. Min Range: -6.0529
Max Act: 5.8654. Min Act: -0.1700
Data Index: 80654 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0529. Min Range: -6.0529
Max Act: 5.8654. Min Act: -0.1700
Data Index: 588696 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0529. Min Range: -6.0529
Max Act: 5.8654. Min Act: -0.1700
Data Index: 3859078 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0529. Min Range: -6.0529
Max Act: 5.8966. Min Act: -0.1700
Data Index: 6659363 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0529. Min Range: -6.0529
Max Act: 5.8654. Min Act: -0.1700
Data Index: 8195994 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0529. Min Range: -6.0529
Max Act: 5.8654. Min Act: -0.1700
Data Index: 4663998 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0529. Min Range: -6.0529
Max Act: 5.8029. Min Act: -0.1700
Data Index: 7097317 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0529. Min Range: -6.0529
Max Act: 5.8341. Min Act: -0.1700
Data Index: 3444578 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0529. Min Range: -6.0529
Max Act: 5.8029. Min Act: -0.1700
Data Index: 5075893 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0529. Min Range: -6.0529
Max Act: 5.8029. Min Act: -0.1700
Data Index: 5155198 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0529. Min Range: -6.0529
Max Act: 5.8341. Min Act: -0.1700
Data Index: 6939654 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0529. Min Range: -6.0529
Max Act: 5.8029. Min Act: -0.1700
Data Index: 6388052 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19