Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5254 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6499. Min Range: -7.6499
Max Act: 7.6499. Min Act: -0.1700
Data Index: 4060524 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6499. Min Range: -7.6499
Max Act: 7.1499. Min Act: -0.1700
Data Index: 2799992 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6499. Min Range: -7.6499
Max Act: 7.0249. Min Act: -0.1700
Data Index: 2582833 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6499. Min Range: -7.6499
Max Act: 6.9936. Min Act: -0.1700
Data Index: 5966051 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6499. Min Range: -7.6499
Max Act: 6.9936. Min Act: -0.1700
Data Index: 3846201 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6499. Min Range: -7.6499
Max Act: 6.9936. Min Act: -0.1700
Data Index: 2192506 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6499. Min Range: -7.6499
Max Act: 6.8999. Min Act: -0.1700
Data Index: 6127664 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6499. Min Range: -7.6499
Max Act: 6.8686. Min Act: -0.1700
Data Index: 2192507 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6499. Min Range: -7.6499
Max Act: 6.8374. Min Act: -0.1700
Data Index: 2312249 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6499. Min Range: -7.6499
Max Act: 6.8374. Min Act: -0.1700
Data Index: 3053633 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6499. Min Range: -7.6499
Max Act: 6.8061. Min Act: -0.1700
Data Index: 1062176 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6499. Min Range: -7.6499
Max Act: 6.8061. Min Act: -0.1700
Data Index: 7252945 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6499. Min Range: -7.6499
Max Act: 6.8061. Min Act: -0.1700
Data Index: 4064188 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6499. Min Range: -7.6499
Max Act: 6.7436. Min Act: -0.1700
Data Index: 1546402 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6499. Min Range: -7.6499
Max Act: 6.7436. Min Act: -0.1700
Data Index: 110607 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6499. Min Range: -7.6499
Max Act: 6.7436. Min Act: -0.1700
Data Index: 4882832 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6499. Min Range: -7.6499
Max Act: 6.7124. Min Act: -0.1700
Data Index: 765624 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6499. Min Range: -7.6499
Max Act: 6.7124. Min Act: -0.1700
Data Index: 7288315 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6499. Min Range: -7.6499
Max Act: 6.7124. Min Act: -0.1700
Data Index: 2459994 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6499. Min Range: -7.6499
Max Act: 6.6811. Min Act: -0.1700
Data Index: 5449267 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19