Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3067 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.5828. Min Range: -1.5828
Max Act: 1.5828. Min Act: -0.1700
Data Index: 733697 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5828. Min Range: -1.5828
Max Act: 1.5654. Min Act: -0.1700
Data Index: 3481670 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5828. Min Range: -1.5828
Max Act: 1.5303. Min Act: -0.1700
Data Index: 5230454 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5828. Min Range: -1.5828
Max Act: 1.5303. Min Act: -0.1700
Data Index: 6834385 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5828. Min Range: -1.5828
Max Act: 1.5128. Min Act: -0.1700
Data Index: 3988716 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5828. Min Range: -1.5828
Max Act: 1.5128. Min Act: -0.1700
Data Index: 2595412 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5828. Min Range: -1.5828
Max Act: 1.5128. Min Act: -0.1700
Data Index: 5258433 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5828. Min Range: -1.5828
Max Act: 1.5128. Min Act: -0.1700
Data Index: 7107187 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5828. Min Range: -1.5828
Max Act: 1.4952. Min Act: -0.1700
Data Index: 1787851 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5828. Min Range: -1.5828
Max Act: 1.4952. Min Act: -0.1700
Data Index: 8173034 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5828. Min Range: -1.5828
Max Act: 1.4952. Min Act: -0.1700
Data Index: 628927 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5828. Min Range: -1.5828
Max Act: 1.4952. Min Act: -0.1700
Data Index: 4139302 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5828. Min Range: -1.5828
Max Act: 1.4777. Min Act: -0.1700
Data Index: 3508640 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5828. Min Range: -1.5828
Max Act: 1.4777. Min Act: -0.1700
Data Index: 2942505 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5828. Min Range: -1.5828
Max Act: 1.4777. Min Act: -0.1700
Data Index: 7895317 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5828. Min Range: -1.5828
Max Act: 1.4777. Min Act: -0.1700
Data Index: 6050610 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5828. Min Range: -1.5828
Max Act: 1.4777. Min Act: -0.1700
Data Index: 898385 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5828. Min Range: -1.5828
Max Act: 1.4601. Min Act: -0.1700
Data Index: 4976503 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5828. Min Range: -1.5828
Max Act: 1.4601. Min Act: -0.1700
Data Index: 4064766 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5828. Min Range: -1.5828
Max Act: 1.4601. Min Act: -0.1700
Data Index: 1296207 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19