Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3773 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0089. Min Range: -6.0089
Max Act: 6.0089. Min Act: -0.1700
Data Index: 6490200 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0089. Min Range: -6.0089
Max Act: 5.9776. Min Act: -0.1700
Data Index: 3478623 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0089. Min Range: -6.0089
Max Act: 5.9464. Min Act: -0.1700
Data Index: 687735 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0089. Min Range: -6.0089
Max Act: 5.8839. Min Act: -0.1700
Data Index: 4861832 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0089. Min Range: -6.0089
Max Act: 5.8839. Min Act: -0.1700
Data Index: 5298027 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0089. Min Range: -6.0089
Max Act: 5.8839. Min Act: -0.1700
Data Index: 43946 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0089. Min Range: -6.0089
Max Act: 5.8526. Min Act: -0.1700
Data Index: 5303191 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0089. Min Range: -6.0089
Max Act: 5.8526. Min Act: -0.1700
Data Index: 7529321 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0089. Min Range: -6.0089
Max Act: 5.8526. Min Act: -0.1700
Data Index: 4267682 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0089. Min Range: -6.0089
Max Act: 5.8214. Min Act: -0.1700
Data Index: 3802725 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0089. Min Range: -6.0089
Max Act: 5.8214. Min Act: -0.1700
Data Index: 5569842 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0089. Min Range: -6.0089
Max Act: 5.7901. Min Act: -0.1700
Data Index: 1305570 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0089. Min Range: -6.0089
Max Act: 5.7901. Min Act: -0.1700
Data Index: 6665 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0089. Min Range: -6.0089
Max Act: 5.7901. Min Act: -0.1700
Data Index: 6674662 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0089. Min Range: -6.0089
Max Act: 5.8214. Min Act: -0.1700
Data Index: 5283614 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0089. Min Range: -6.0089
Max Act: 5.8214. Min Act: -0.1700
Data Index: 6670623 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0089. Min Range: -6.0089
Max Act: 5.7589. Min Act: -0.1700
Data Index: 6075355 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0089. Min Range: -6.0089
Max Act: 5.7589. Min Act: -0.1700
Data Index: 5575805 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0089. Min Range: -6.0089
Max Act: 5.7589. Min Act: -0.1700
Data Index: 2681743 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0089. Min Range: -6.0089
Max Act: 5.7901. Min Act: -0.1700
Data Index: 4158732 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19