Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1602 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9225. Min Range: -4.9225
Max Act: 4.8913. Min Act: -0.1700
Data Index: 5091827 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9225. Min Range: -4.9225
Max Act: 4.9225. Min Act: -0.1700
Data Index: 6981061 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9225. Min Range: -4.9225
Max Act: 4.8600. Min Act: -0.1700
Data Index: 5104664 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9225. Min Range: -4.9225
Max Act: 4.7663. Min Act: -0.1700
Data Index: 2506742 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9225. Min Range: -4.9225
Max Act: 4.7663. Min Act: -0.1700
Data Index: 2330305 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9225. Min Range: -4.9225
Max Act: 4.7663. Min Act: -0.1700
Data Index: 6497000 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9225. Min Range: -4.9225
Max Act: 4.7663. Min Act: -0.1700
Data Index: 914961 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9225. Min Range: -4.9225
Max Act: 4.7350. Min Act: -0.1700
Data Index: 2030189 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9225. Min Range: -4.9225
Max Act: 4.7038. Min Act: -0.1700
Data Index: 2410901 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9225. Min Range: -4.9225
Max Act: 4.6725. Min Act: -0.1700
Data Index: 8648957 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9225. Min Range: -4.9225
Max Act: 4.7038. Min Act: -0.1700
Data Index: 4019941 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9225. Min Range: -4.9225
Max Act: 4.6413. Min Act: -0.1700
Data Index: 1828532 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9225. Min Range: -4.9225
Max Act: 4.6413. Min Act: -0.1700
Data Index: 3378021 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9225. Min Range: -4.9225
Max Act: 4.6725. Min Act: -0.1700
Data Index: 6181403 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9225. Min Range: -4.9225
Max Act: 4.6100. Min Act: -0.1700
Data Index: 4992944 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9225. Min Range: -4.9225
Max Act: 4.6100. Min Act: -0.1700
Data Index: 7013115 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9225. Min Range: -4.9225
Max Act: 4.6100. Min Act: -0.1700
Data Index: 8162038 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9225. Min Range: -4.9225
Max Act: 4.6100. Min Act: -0.1700
Data Index: 6160370 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9225. Min Range: -4.9225
Max Act: 4.5788. Min Act: -0.1700
Data Index: 5153859 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9225. Min Range: -4.9225
Max Act: 4.5788. Min Act: -0.1700
Data Index: 6551793 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19