Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2666 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0368. Min Range: -6.0368
Max Act: 6.0368. Min Act: -0.1700
Data Index: 2447220 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0368. Min Range: -6.0368
Max Act: 5.8493. Min Act: -0.1700
Data Index: 7926075 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0368. Min Range: -6.0368
Max Act: 5.8493. Min Act: -0.1700
Data Index: 3036682 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0368. Min Range: -6.0368
Max Act: 5.8493. Min Act: -0.1700
Data Index: 4703226 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0368. Min Range: -6.0368
Max Act: 5.8180. Min Act: -0.1700
Data Index: 1197790 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0368. Min Range: -6.0368
Max Act: 5.7243. Min Act: -0.1700
Data Index: 1391092 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0368. Min Range: -6.0368
Max Act: 5.7243. Min Act: -0.1700
Data Index: 4979377 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0368. Min Range: -6.0368
Max Act: 5.6305. Min Act: -0.1700
Data Index: 3334713 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0368. Min Range: -6.0368
Max Act: 5.5993. Min Act: -0.1700
Data Index: 1635309 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0368. Min Range: -6.0368
Max Act: 5.5993. Min Act: -0.1700
Data Index: 8777870 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0368. Min Range: -6.0368
Max Act: 5.5680. Min Act: -0.1700
Data Index: 8178005 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0368. Min Range: -6.0368
Max Act: 5.5680. Min Act: -0.1700
Data Index: 4927020 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0368. Min Range: -6.0368
Max Act: 5.4430. Min Act: -0.1700
Data Index: 2227148 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0368. Min Range: -6.0368
Max Act: 5.5993. Min Act: -0.1700
Data Index: 2053518 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0368. Min Range: -6.0368
Max Act: 5.5055. Min Act: -0.1700
Data Index: 7142240 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0368. Min Range: -6.0368
Max Act: 5.5055. Min Act: -0.1700
Data Index: 4927021 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0368. Min Range: -6.0368
Max Act: 5.5680. Min Act: -0.1700
Data Index: 6823029 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0368. Min Range: -6.0368
Max Act: 5.4430. Min Act: -0.1700
Data Index: 6711130 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0368. Min Range: -6.0368
Max Act: 5.4743. Min Act: -0.1700
Data Index: 6584665 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0368. Min Range: -6.0368
Max Act: 5.5368. Min Act: -0.1700
Data Index: 6749743 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19