Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3563 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.6051. Min Act: -0.1700
Data Index: 3171809 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.4798. Min Act: -0.1700
Data Index: 8102286 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.4798. Min Act: -0.1700
Data Index: 7131344 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.4641. Min Act: -0.1700
Data Index: 8594198 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.4485. Min Act: -0.1700
Data Index: 412994 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.4328. Min Act: -0.1700
Data Index: 262442 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.4328. Min Act: -0.1700
Data Index: 1836295 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.4014. Min Act: -0.1700
Data Index: 1836287 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.3858. Min Act: -0.1700
Data Index: 3018251 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.3073. Min Act: -0.1700
Data Index: 4651296 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.3073. Min Act: -0.1700
Data Index: 6302505 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.2916. Min Act: -0.1700
Data Index: 7289839 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.2759. Min Act: -0.1700
Data Index: 6063917 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.2602. Min Act: -0.1700
Data Index: 8521738 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.2288. Min Act: -0.1700
Data Index: 8263480 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.2445. Min Act: -0.1700
Data Index: 1767928 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.2288. Min Act: -0.1700
Data Index: 7015671 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.2131. Min Act: -0.1700
Data Index: 3887181 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.2131. Min Act: -0.1700
Data Index: 8660696 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.1973. Min Act: -0.1700
Data Index: 8564953 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19