Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4653 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7523. Min Range: -5.7523
Max Act: 5.7523. Min Act: -0.1700
Data Index: 6190472 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7523. Min Range: -5.7523
Max Act: 5.7211. Min Act: -0.1700
Data Index: 5612581 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7523. Min Range: -5.7523
Max Act: 5.6898. Min Act: -0.1700
Data Index: 7061170 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7523. Min Range: -5.7523
Max Act: 5.6898. Min Act: -0.1700
Data Index: 7947163 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7523. Min Range: -5.7523
Max Act: 5.6898. Min Act: -0.1693
Data Index: 1550993 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7523. Min Range: -5.7523
Max Act: 5.6586. Min Act: -0.1700
Data Index: 4251230 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7523. Min Range: -5.7523
Max Act: 5.6586. Min Act: -0.1700
Data Index: 4756637 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7523. Min Range: -5.7523
Max Act: 5.6586. Min Act: -0.1700
Data Index: 8672617 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7523. Min Range: -5.7523
Max Act: 5.5961. Min Act: -0.1700
Data Index: 6353254 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7523. Min Range: -5.7523
Max Act: 5.5961. Min Act: -0.1700
Data Index: 2156581 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7523. Min Range: -5.7523
Max Act: 5.5961. Min Act: -0.1700
Data Index: 1662057 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7523. Min Range: -5.7523
Max Act: 5.5648. Min Act: -0.1700
Data Index: 1143918 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7523. Min Range: -5.7523
Max Act: 5.5648. Min Act: -0.1700
Data Index: 7722834 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7523. Min Range: -5.7523
Max Act: 5.5336. Min Act: -0.1700
Data Index: 2900145 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7523. Min Range: -5.7523
Max Act: 5.5336. Min Act: -0.1700
Data Index: 5532598 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7523. Min Range: -5.7523
Max Act: 5.5336. Min Act: -0.1700
Data Index: 417179 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7523. Min Range: -5.7523
Max Act: 5.5336. Min Act: -0.1700
Data Index: 1943538 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7523. Min Range: -5.7523
Max Act: 5.5023. Min Act: -0.1700
Data Index: 3934118 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7523. Min Range: -5.7523
Max Act: 5.5023. Min Act: -0.1700
Data Index: 4082891 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7523. Min Range: -5.7523
Max Act: 5.5023. Min Act: -0.1700
Data Index: 7245219 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19