Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 404 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8039. Min Range: -5.8039
Max Act: 5.8039. Min Act: -0.1700
Data Index: 3084388 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8039. Min Range: -5.8039
Max Act: 5.7727. Min Act: -0.1700
Data Index: 3134754 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8039. Min Range: -5.8039
Max Act: 5.7414. Min Act: -0.1700
Data Index: 7071849 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8039. Min Range: -5.8039
Max Act: 5.7102. Min Act: -0.1700
Data Index: 4398954 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8039. Min Range: -5.8039
Max Act: 5.6789. Min Act: -0.1700
Data Index: 5944532 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8039. Min Range: -5.8039
Max Act: 5.6477. Min Act: -0.1700
Data Index: 6077150 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8039. Min Range: -5.8039
Max Act: 5.6164. Min Act: -0.1700
Data Index: 580015 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8039. Min Range: -5.8039
Max Act: 5.5539. Min Act: -0.1700
Data Index: 1640253 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8039. Min Range: -5.8039
Max Act: 5.5227. Min Act: -0.1700
Data Index: 7248526 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8039. Min Range: -5.8039
Max Act: 5.5539. Min Act: -0.1700
Data Index: 5696337 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8039. Min Range: -5.8039
Max Act: 5.5539. Min Act: -0.1700
Data Index: 60189 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8039. Min Range: -5.8039
Max Act: 5.5227. Min Act: -0.1700
Data Index: 2124093 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8039. Min Range: -5.8039
Max Act: 5.5227. Min Act: -0.1700
Data Index: 7092178 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8039. Min Range: -5.8039
Max Act: 5.4914. Min Act: -0.1700
Data Index: 8611674 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8039. Min Range: -5.8039
Max Act: 5.4914. Min Act: -0.1700
Data Index: 1245900 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8039. Min Range: -5.8039
Max Act: 5.4914. Min Act: -0.1700
Data Index: 6273126 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8039. Min Range: -5.8039
Max Act: 5.4914. Min Act: -0.1700
Data Index: 6010954 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8039. Min Range: -5.8039
Max Act: 5.4602. Min Act: -0.1700
Data Index: 4405183 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8039. Min Range: -5.8039
Max Act: 5.4289. Min Act: -0.1700
Data Index: 5467871 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8039. Min Range: -5.8039
Max Act: 5.4289. Min Act: -0.1700
Data Index: 281571 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19