Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 179 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8864. Min Range: -2.8864
Max Act: 2.8864. Min Act: -0.1700
Data Index: 4359896 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8864. Min Range: -2.8864
Max Act: 2.8546. Min Act: -0.1700
Data Index: 2874417 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8864. Min Range: -2.8864
Max Act: 2.8546. Min Act: -0.1700
Data Index: 6088636 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8864. Min Range: -2.8864
Max Act: 2.8546. Min Act: -0.1700
Data Index: 5842423 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8864. Min Range: -2.8864
Max Act: 2.8228. Min Act: -0.1700
Data Index: 3931202 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8864. Min Range: -2.8864
Max Act: 2.8069. Min Act: -0.1700
Data Index: 3931200 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8864. Min Range: -2.8864
Max Act: 2.8228. Min Act: -0.1700
Data Index: 4546829 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8864. Min Range: -2.8864
Max Act: 2.8228. Min Act: -0.1700
Data Index: 3318667 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8864. Min Range: -2.8864
Max Act: 2.8069. Min Act: -0.1700
Data Index: 6433589 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8864. Min Range: -2.8864
Max Act: 2.8069. Min Act: -0.1700
Data Index: 6433592 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8864. Min Range: -2.8864
Max Act: 2.8069. Min Act: -0.1700
Data Index: 1080294 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8864. Min Range: -2.8864
Max Act: 2.7910. Min Act: -0.1700
Data Index: 6972672 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8864. Min Range: -2.8864
Max Act: 2.8069. Min Act: -0.1700
Data Index: 3307411 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8864. Min Range: -2.8864
Max Act: 2.7910. Min Act: -0.1700
Data Index: 1160548 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8864. Min Range: -2.8864
Max Act: 2.7910. Min Act: -0.1700
Data Index: 2001653 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8864. Min Range: -2.8864
Max Act: 2.7910. Min Act: -0.1700
Data Index: 6433591 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8864. Min Range: -2.8864
Max Act: 2.7751. Min Act: -0.1700
Data Index: 5732219 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8864. Min Range: -2.8864
Max Act: 2.7910. Min Act: -0.1700
Data Index: 3307410 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8864. Min Range: -2.8864
Max Act: 2.7751. Min Act: -0.1700
Data Index: 2192509 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8864. Min Range: -2.8864
Max Act: 2.7751. Min Act: -0.1700
Data Index: 8547583 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19