Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2996 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6043. Min Range: -4.6043
Max Act: 4.6043. Min Act: -0.1700
Data Index: 4693375 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6043. Min Range: -4.6043
Max Act: 4.6043. Min Act: -0.1700
Data Index: 6580538 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6043. Min Range: -4.6043
Max Act: 4.5418. Min Act: -0.1700
Data Index: 3484100 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6043. Min Range: -4.6043
Max Act: 4.5106. Min Act: -0.1700
Data Index: 1531487 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6043. Min Range: -4.6043
Max Act: 4.5106. Min Act: -0.1700
Data Index: 1065490 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6043. Min Range: -4.6043
Max Act: 4.4793. Min Act: -0.1700
Data Index: 4588064 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6043. Min Range: -4.6043
Max Act: 4.4793. Min Act: -0.1700
Data Index: 3298651 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6043. Min Range: -4.6043
Max Act: 4.4793. Min Act: -0.1700
Data Index: 4006018 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6043. Min Range: -4.6043
Max Act: 4.4481. Min Act: -0.1700
Data Index: 3640851 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6043. Min Range: -4.6043
Max Act: 4.4168. Min Act: -0.1700
Data Index: 4575057 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6043. Min Range: -4.6043
Max Act: 4.4481. Min Act: -0.1700
Data Index: 7414356 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6043. Min Range: -4.6043
Max Act: 4.3856. Min Act: -0.1700
Data Index: 4828771 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6043. Min Range: -4.6043
Max Act: 4.3856. Min Act: -0.1700
Data Index: 1800584 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6043. Min Range: -4.6043
Max Act: 4.3856. Min Act: -0.1700
Data Index: 5908531 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6043. Min Range: -4.6043
Max Act: 4.3856. Min Act: -0.1700
Data Index: 7916220 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6043. Min Range: -4.6043
Max Act: 4.3856. Min Act: -0.1700
Data Index: 1525995 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6043. Min Range: -4.6043
Max Act: 4.4168. Min Act: -0.1700
Data Index: 8490236 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6043. Min Range: -4.6043
Max Act: 4.3543. Min Act: -0.1700
Data Index: 3949409 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6043. Min Range: -4.6043
Max Act: 4.3856. Min Act: -0.1700
Data Index: 1775550 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6043. Min Range: -4.6043
Max Act: 4.3856. Min Act: -0.1700
Data Index: 551483 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19