Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3728 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3051. Min Range: -5.3051
Max Act: 5.3051. Min Act: -0.1700
Data Index: 3518781 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3051. Min Range: -5.3051
Max Act: 5.2426. Min Act: -0.1700
Data Index: 4346378 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3051. Min Range: -5.3051
Max Act: 5.2113. Min Act: -0.1700
Data Index: 270222 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3051. Min Range: -5.3051
Max Act: 5.2113. Min Act: -0.1700
Data Index: 463169 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3051. Min Range: -5.3051
Max Act: 5.1801. Min Act: -0.1700
Data Index: 6900859 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3051. Min Range: -5.3051
Max Act: 5.1488. Min Act: -0.1700
Data Index: 8191187 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3051. Min Range: -5.3051
Max Act: 5.1176. Min Act: -0.1700
Data Index: 442318 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3051. Min Range: -5.3051
Max Act: 5.1488. Min Act: -0.1700
Data Index: 5056412 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3051. Min Range: -5.3051
Max Act: 5.1176. Min Act: -0.1700
Data Index: 1136343 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3051. Min Range: -5.3051
Max Act: 5.1488. Min Act: -0.1700
Data Index: 5462840 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3051. Min Range: -5.3051
Max Act: 5.1176. Min Act: -0.1700
Data Index: 7712323 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3051. Min Range: -5.3051
Max Act: 5.0863. Min Act: -0.1700
Data Index: 673615 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3051. Min Range: -5.3051
Max Act: 5.0863. Min Act: -0.1700
Data Index: 5239525 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3051. Min Range: -5.3051
Max Act: 5.0863. Min Act: -0.1700
Data Index: 6129068 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3051. Min Range: -5.3051
Max Act: 5.0863. Min Act: -0.1700
Data Index: 800017 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3051. Min Range: -5.3051
Max Act: 5.0551. Min Act: -0.1700
Data Index: 4564858 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3051. Min Range: -5.3051
Max Act: 5.0551. Min Act: -0.1700
Data Index: 6319463 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3051. Min Range: -5.3051
Max Act: 5.0551. Min Act: -0.1700
Data Index: 2670011 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3051. Min Range: -5.3051
Max Act: 5.0551. Min Act: -0.1700
Data Index: 644837 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3051. Min Range: -5.3051
Max Act: 4.9926. Min Act: -0.1700
Data Index: 1963653 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19