Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3073 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4401. Min Range: -5.4401
Max Act: 5.4401. Min Act: -0.1700
Data Index: 3121791 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4401. Min Range: -5.4401
Max Act: 5.3151. Min Act: -0.1700
Data Index: 6222380 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4401. Min Range: -5.4401
Max Act: 5.3151. Min Act: -0.1700
Data Index: 1347512 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4401. Min Range: -5.4401
Max Act: 5.3151. Min Act: -0.1700
Data Index: 5491311 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4401. Min Range: -5.4401
Max Act: 5.3151. Min Act: -0.1700
Data Index: 2774945 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4401. Min Range: -5.4401
Max Act: 5.2838. Min Act: -0.1700
Data Index: 548651 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4401. Min Range: -5.4401
Max Act: 5.2526. Min Act: -0.1700
Data Index: 6645438 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4401. Min Range: -5.4401
Max Act: 5.2526. Min Act: -0.1700
Data Index: 1636436 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4401. Min Range: -5.4401
Max Act: 5.2213. Min Act: -0.1700
Data Index: 1905451 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4401. Min Range: -5.4401
Max Act: 5.2213. Min Act: -0.1700
Data Index: 2994103 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4401. Min Range: -5.4401
Max Act: 5.1901. Min Act: -0.1700
Data Index: 3272839 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4401. Min Range: -5.4401
Max Act: 5.2213. Min Act: -0.1700
Data Index: 1694132 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4401. Min Range: -5.4401
Max Act: 5.2213. Min Act: -0.1700
Data Index: 7803327 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4401. Min Range: -5.4401
Max Act: 5.2213. Min Act: -0.1700
Data Index: 1785343 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4401. Min Range: -5.4401
Max Act: 5.2213. Min Act: -0.1700
Data Index: 6394809 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4401. Min Range: -5.4401
Max Act: 5.1901. Min Act: -0.1700
Data Index: 5008830 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4401. Min Range: -5.4401
Max Act: 5.1901. Min Act: -0.1700
Data Index: 3121786 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4401. Min Range: -5.4401
Max Act: 5.1901. Min Act: -0.1700
Data Index: 230247 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4401. Min Range: -5.4401
Max Act: 5.1901. Min Act: -0.1700
Data Index: 3818929 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4401. Min Range: -5.4401
Max Act: 5.1901. Min Act: -0.1700
Data Index: 6228842 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19