Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1740 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7600. Min Range: -1.7600
Max Act: 1.7600. Min Act: -0.1700
Data Index: 3597936 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7600. Min Range: -1.7600
Max Act: 1.6907. Min Act: -0.1700
Data Index: 1936184 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7600. Min Range: -1.7600
Max Act: 1.6647. Min Act: -0.1700
Data Index: 7389941 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7600. Min Range: -1.7600
Max Act: 1.6560. Min Act: -0.1700
Data Index: 1258117 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7600. Min Range: -1.7600
Max Act: 1.6386. Min Act: -0.1700
Data Index: 3988452 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7600. Min Range: -1.7600
Max Act: 1.6473. Min Act: -0.1700
Data Index: 5184713 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7600. Min Range: -1.7600
Max Act: 1.6211. Min Act: -0.1698
Data Index: 2700951 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7600. Min Range: -1.7600
Max Act: 1.6299. Min Act: -0.1700
Data Index: 8794573 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7600. Min Range: -1.7600
Max Act: 1.6299. Min Act: -0.1689
Data Index: 6294562 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7600. Min Range: -1.7600
Max Act: 1.6299. Min Act: -0.1695
Data Index: 8389802 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7600. Min Range: -1.7600
Max Act: 1.6211. Min Act: -0.1700
Data Index: 4000364 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7600. Min Range: -1.7600
Max Act: 1.6037. Min Act: -0.1700
Data Index: 6476571 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7600. Min Range: -1.7600
Max Act: 1.6037. Min Act: -0.1700
Data Index: 1256696 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7600. Min Range: -1.7600
Max Act: 1.6124. Min Act: -0.1700
Data Index: 6675825 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7600. Min Range: -1.7600
Max Act: 1.6037. Min Act: -0.1699
Data Index: 6432311 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7600. Min Range: -1.7600
Max Act: 1.5950. Min Act: -0.1700
Data Index: 6831245 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7600. Min Range: -1.7600
Max Act: 1.5950. Min Act: -0.1700
Data Index: 1585767 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7600. Min Range: -1.7600
Max Act: 1.6037. Min Act: -0.1700
Data Index: 7221855 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7600. Min Range: -1.7600
Max Act: 1.5950. Min Act: -0.1700
Data Index: 4561928 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7600. Min Range: -1.7600
Max Act: 1.5950. Min Act: -0.1700
Data Index: 1836543 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19