Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2166 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.3793. Min Range: -6.3793
Max Act: 6.3793. Min Act: -0.1700
Data Index: 7519005 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3793. Min Range: -6.3793
Max Act: 6.3480. Min Act: -0.1700
Data Index: 7720056 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3793. Min Range: -6.3793
Max Act: 6.0668. Min Act: -0.1700
Data Index: 3743670 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3793. Min Range: -6.3793
Max Act: 6.0043. Min Act: -0.1700
Data Index: 76353 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3793. Min Range: -6.3793
Max Act: 5.9730. Min Act: -0.1700
Data Index: 3712024 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3793. Min Range: -6.3793
Max Act: 5.9418. Min Act: -0.1700
Data Index: 6455111 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3793. Min Range: -6.3793
Max Act: 5.8168. Min Act: -0.1700
Data Index: 7579570 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3793. Min Range: -6.3793
Max Act: 5.8168. Min Act: -0.1700
Data Index: 3890640 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3793. Min Range: -6.3793
Max Act: 5.8480. Min Act: -0.1700
Data Index: 8356609 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3793. Min Range: -6.3793
Max Act: 5.7855. Min Act: -0.1700
Data Index: 8769088 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3793. Min Range: -6.3793
Max Act: 5.6918. Min Act: -0.1700
Data Index: 3454038 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3793. Min Range: -6.3793
Max Act: 5.5980. Min Act: -0.1700
Data Index: 4973121 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3793. Min Range: -6.3793
Max Act: 5.5355. Min Act: -0.1700
Data Index: 4493030 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3793. Min Range: -6.3793
Max Act: 5.6605. Min Act: -0.1700
Data Index: 1507857 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3793. Min Range: -6.3793
Max Act: 5.6293. Min Act: -0.1700
Data Index: 1202386 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3793. Min Range: -6.3793
Max Act: 5.5355. Min Act: -0.1700
Data Index: 165318 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3793. Min Range: -6.3793
Max Act: 5.5668. Min Act: -0.1700
Data Index: 5233632 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3793. Min Range: -6.3793
Max Act: 5.5980. Min Act: -0.1700
Data Index: 2976752 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3793. Min Range: -6.3793
Max Act: 5.5355. Min Act: -0.1700
Data Index: 3772206 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3793. Min Range: -6.3793
Max Act: 5.5355. Min Act: -0.1700
Data Index: 8490331 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #19