Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4040 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1977. Min Range: -6.1977
Max Act: 6.1977. Min Act: -0.1700
Data Index: 8071230 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1977. Min Range: -6.1977
Max Act: 5.9789. Min Act: -0.1700
Data Index: 1743340 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1977. Min Range: -6.1977
Max Act: 5.9789. Min Act: -0.1700
Data Index: 6809061 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1977. Min Range: -6.1977
Max Act: 5.9164. Min Act: -0.1700
Data Index: 526147 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1977. Min Range: -6.1977
Max Act: 5.8539. Min Act: -0.1700
Data Index: 5549167 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1977. Min Range: -6.1977
Max Act: 5.8227. Min Act: -0.1700
Data Index: 8291782 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1977. Min Range: -6.1977
Max Act: 5.8227. Min Act: -0.1700
Data Index: 783553 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1977. Min Range: -6.1977
Max Act: 5.7914. Min Act: -0.1700
Data Index: 2209105 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1977. Min Range: -6.1977
Max Act: 5.7914. Min Act: -0.1700
Data Index: 4402525 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1977. Min Range: -6.1977
Max Act: 5.7602. Min Act: -0.1700
Data Index: 1321369 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1977. Min Range: -6.1977
Max Act: 5.7602. Min Act: -0.1700
Data Index: 4034215 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1977. Min Range: -6.1977
Max Act: 5.7602. Min Act: -0.1700
Data Index: 1510937 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1977. Min Range: -6.1977
Max Act: 5.7289. Min Act: -0.1700
Data Index: 893213 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1977. Min Range: -6.1977
Max Act: 5.7289. Min Act: -0.1700
Data Index: 1709394 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1977. Min Range: -6.1977
Max Act: 5.7289. Min Act: -0.1700
Data Index: 3152158 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1977. Min Range: -6.1977
Max Act: 5.7289. Min Act: -0.1700
Data Index: 6616010 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1977. Min Range: -6.1977
Max Act: 5.6977. Min Act: -0.1700
Data Index: 6229368 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1977. Min Range: -6.1977
Max Act: 5.7289. Min Act: -0.1700
Data Index: 2884964 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1977. Min Range: -6.1977
Max Act: 5.7289. Min Act: -0.1700
Data Index: 2404680 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1977. Min Range: -6.1977
Max Act: 5.7289. Min Act: -0.1700
Data Index: 982222 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19