Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3218 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0312. Min Range: -7.0312
Max Act: 7.0312. Min Act: -0.1700
Data Index: 398634 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0312. Min Range: -7.0312
Max Act: 7.0312. Min Act: -0.1700
Data Index: 5073826 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0312. Min Range: -7.0312
Max Act: 6.9687. Min Act: -0.1700
Data Index: 1858518 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0312. Min Range: -7.0312
Max Act: 6.9062. Min Act: -0.1700
Data Index: 6796268 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0312. Min Range: -7.0312
Max Act: 6.8124. Min Act: -0.1700
Data Index: 1799654 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0312. Min Range: -7.0312
Max Act: 6.8124. Min Act: -0.1700
Data Index: 5688047 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0312. Min Range: -7.0312
Max Act: 6.7187. Min Act: -0.1700
Data Index: 8728584 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0312. Min Range: -7.0312
Max Act: 6.6874. Min Act: -0.1700
Data Index: 3481691 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0312. Min Range: -7.0312
Max Act: 6.7187. Min Act: -0.1700
Data Index: 6663479 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0312. Min Range: -7.0312
Max Act: 6.6562. Min Act: -0.1700
Data Index: 4623669 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0312. Min Range: -7.0312
Max Act: 6.6874. Min Act: -0.1700
Data Index: 3360911 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0312. Min Range: -7.0312
Max Act: 6.6249. Min Act: -0.1700
Data Index: 4871648 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0312. Min Range: -7.0312
Max Act: 6.6249. Min Act: -0.1700
Data Index: 6071684 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0312. Min Range: -7.0312
Max Act: 6.5937. Min Act: -0.1700
Data Index: 470538 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0312. Min Range: -7.0312
Max Act: 6.5937. Min Act: -0.1700
Data Index: 4233551 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0312. Min Range: -7.0312
Max Act: 6.5312. Min Act: -0.1700
Data Index: 590395 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0312. Min Range: -7.0312
Max Act: 6.5312. Min Act: -0.1700
Data Index: 70129 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0312. Min Range: -7.0312
Max Act: 6.5312. Min Act: -0.1700
Data Index: 5363171 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0312. Min Range: -7.0312
Max Act: 6.4999. Min Act: -0.1700
Data Index: 6299761 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0312. Min Range: -7.0312
Max Act: 6.4999. Min Act: -0.1700
Data Index: 2853820 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19