Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5404 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5371. Min Range: -2.5371
Max Act: 2.5371. Min Act: -0.1700
Data Index: 4988735 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5371. Min Range: -2.5371
Max Act: 2.4560. Min Act: -0.1700
Data Index: 893676 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5371. Min Range: -2.5371
Max Act: 2.4235. Min Act: -0.1700
Data Index: 5841983 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5371. Min Range: -2.5371
Max Act: 2.4072. Min Act: -0.1700
Data Index: 4750180 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5371. Min Range: -2.5371
Max Act: 2.3909. Min Act: -0.1700
Data Index: 3000262 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5371. Min Range: -2.5371
Max Act: 2.3909. Min Act: -0.1700
Data Index: 7977659 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5371. Min Range: -2.5371
Max Act: 2.3909. Min Act: -0.1700
Data Index: 7911002 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5371. Min Range: -2.5371
Max Act: 2.3745. Min Act: -0.1700
Data Index: 2384419 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5371. Min Range: -2.5371
Max Act: 2.3745. Min Act: -0.1699
Data Index: 4107675 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5371. Min Range: -2.5371
Max Act: 2.3745. Min Act: -0.1700
Data Index: 4909800 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5371. Min Range: -2.5371
Max Act: 2.3582. Min Act: -0.1700
Data Index: 3819534 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5371. Min Range: -2.5371
Max Act: 2.3745. Min Act: -0.1700
Data Index: 6171798 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5371. Min Range: -2.5371
Max Act: 2.3582. Min Act: -0.1700
Data Index: 1750028 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5371. Min Range: -2.5371
Max Act: 2.3582. Min Act: -0.1700
Data Index: 1094235 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5371. Min Range: -2.5371
Max Act: 2.3418. Min Act: -0.1700
Data Index: 4518841 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5371. Min Range: -2.5371
Max Act: 2.3582. Min Act: -0.1700
Data Index: 7982009 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5371. Min Range: -2.5371
Max Act: 2.3582. Min Act: -0.1700
Data Index: 4608481 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5371. Min Range: -2.5371
Max Act: 2.3418. Min Act: -0.1700
Data Index: 7091884 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5371. Min Range: -2.5371
Max Act: 2.3582. Min Act: -0.1700
Data Index: 4989652 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5371. Min Range: -2.5371
Max Act: 2.3418. Min Act: -0.1700
Data Index: 2627016 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19