Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2229. Min Range: -4.2229
Max Act: 4.2229. Min Act: -0.1700
Data Index: 5055348 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2229. Min Range: -4.2229
Max Act: 4.2229. Min Act: -0.1700
Data Index: 8526967 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2229. Min Range: -4.2229
Max Act: 4.2229. Min Act: -0.1700
Data Index: 510384 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2229. Min Range: -4.2229
Max Act: 4.1916. Min Act: -0.1700
Data Index: 2353814 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2229. Min Range: -4.2229
Max Act: 4.1603. Min Act: -0.1700
Data Index: 8708840 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2229. Min Range: -4.2229
Max Act: 4.1603. Min Act: -0.1700
Data Index: 5904374 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2229. Min Range: -4.2229
Max Act: 4.1603. Min Act: -0.1700
Data Index: 1710660 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2229. Min Range: -4.2229
Max Act: 4.1603. Min Act: -0.1700
Data Index: 7591009 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2229. Min Range: -4.2229
Max Act: 4.1291. Min Act: -0.1700
Data Index: 1510387 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2229. Min Range: -4.2229
Max Act: 4.0978. Min Act: -0.1700
Data Index: 1138872 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2229. Min Range: -4.2229
Max Act: 4.0978. Min Act: -0.1700
Data Index: 6503702 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2229. Min Range: -4.2229
Max Act: 4.0978. Min Act: -0.1700
Data Index: 1138870 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2229. Min Range: -4.2229
Max Act: 4.0978. Min Act: -0.1700
Data Index: 2413185 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2229. Min Range: -4.2229
Max Act: 4.0666. Min Act: -0.1700
Data Index: 4629533 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2229. Min Range: -4.2229
Max Act: 4.0978. Min Act: -0.1700
Data Index: 2769347 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2229. Min Range: -4.2229
Max Act: 4.0353. Min Act: -0.1700
Data Index: 1638900 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2229. Min Range: -4.2229
Max Act: 4.0353. Min Act: -0.1700
Data Index: 6703489 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2229. Min Range: -4.2229
Max Act: 4.0041. Min Act: -0.1700
Data Index: 6423618 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2229. Min Range: -4.2229
Max Act: 4.0353. Min Act: -0.1700
Data Index: 1138871 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2229. Min Range: -4.2229
Max Act: 4.0353. Min Act: -0.1700
Data Index: 3077981 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19