Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4259 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0366. Min Range: -5.0366
Max Act: 5.0366. Min Act: -0.1700
Data Index: 8092209 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.8803. Min Act: -0.1700
Data Index: 8568486 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.8178. Min Act: -0.1700
Data Index: 6761723 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.7866. Min Act: -0.1700
Data Index: 2753637 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.8178. Min Act: -0.1700
Data Index: 5296614 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.8178. Min Act: -0.1700
Data Index: 6325648 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.6928. Min Act: -0.1700
Data Index: 3459792 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.6616. Min Act: -0.1700
Data Index: 5322844 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.6616. Min Act: -0.1700
Data Index: 4615934 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.6303. Min Act: -0.1700
Data Index: 5129945 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.5991. Min Act: -0.1700
Data Index: 5911669 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.6303. Min Act: -0.1700
Data Index: 6924955 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.6303. Min Act: -0.1700
Data Index: 7801398 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.5991. Min Act: -0.1700
Data Index: 4361185 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.5678. Min Act: -0.1700
Data Index: 933245 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.5678. Min Act: -0.1700
Data Index: 4652201 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.5366. Min Act: -0.1700
Data Index: 350857 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.5678. Min Act: -0.1700
Data Index: 5019248 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.5366. Min Act: -0.1700
Data Index: 3089261 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.5366. Min Act: -0.1700
Data Index: 422226 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19