Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3968 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7029. Min Range: -5.7029
Max Act: 5.7029. Min Act: -0.1700
Data Index: 7749836 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7029. Min Range: -5.7029
Max Act: 5.6092. Min Act: -0.1700
Data Index: 7641834 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7029. Min Range: -5.7029
Max Act: 5.6092. Min Act: -0.1700
Data Index: 1083536 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7029. Min Range: -5.7029
Max Act: 5.5779. Min Act: -0.1700
Data Index: 3887767 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7029. Min Range: -5.7029
Max Act: 5.5467. Min Act: -0.1700
Data Index: 1300074 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7029. Min Range: -5.7029
Max Act: 5.4529. Min Act: -0.1700
Data Index: 6953087 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7029. Min Range: -5.7029
Max Act: 5.4529. Min Act: -0.1700
Data Index: 5064909 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7029. Min Range: -5.7029
Max Act: 5.3904. Min Act: -0.1700
Data Index: 7037242 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7029. Min Range: -5.7029
Max Act: 5.3904. Min Act: -0.1700
Data Index: 4022817 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7029. Min Range: -5.7029
Max Act: 5.3592. Min Act: -0.1700
Data Index: 7245271 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7029. Min Range: -5.7029
Max Act: 5.3279. Min Act: -0.1700
Data Index: 5479770 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7029. Min Range: -5.7029
Max Act: 5.3279. Min Act: -0.1700
Data Index: 3466069 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7029. Min Range: -5.7029
Max Act: 5.3279. Min Act: -0.1700
Data Index: 7880388 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7029. Min Range: -5.7029
Max Act: 5.3279. Min Act: -0.1700
Data Index: 272288 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7029. Min Range: -5.7029
Max Act: 5.2967. Min Act: -0.1700
Data Index: 6702919 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7029. Min Range: -5.7029
Max Act: 5.2654. Min Act: -0.1700
Data Index: 6184530 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7029. Min Range: -5.7029
Max Act: 5.2654. Min Act: -0.1700
Data Index: 7200848 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7029. Min Range: -5.7029
Max Act: 5.2342. Min Act: -0.1700
Data Index: 6508496 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7029. Min Range: -5.7029
Max Act: 5.2342. Min Act: -0.1700
Data Index: 7967219 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7029. Min Range: -5.7029
Max Act: 5.2654. Min Act: -0.1700
Data Index: 8642623 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19