Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4401 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2717. Min Range: -5.2717
Max Act: 5.2717. Min Act: -0.1700
Data Index: 6117804 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2717. Min Range: -5.2717
Max Act: 5.1780. Min Act: -0.1700
Data Index: 6387394 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2717. Min Range: -5.2717
Max Act: 5.0530. Min Act: -0.1700
Data Index: 5385865 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2717. Min Range: -5.2717
Max Act: 5.0530. Min Act: -0.1700
Data Index: 8020118 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2717. Min Range: -5.2717
Max Act: 5.0217. Min Act: -0.1700
Data Index: 1065153 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2717. Min Range: -5.2717
Max Act: 5.0217. Min Act: -0.1700
Data Index: 4342024 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.9905. Min Act: -0.1700
Data Index: 4942813 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.9905. Min Act: -0.1700
Data Index: 5467104 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.9905. Min Act: -0.1700
Data Index: 1689186 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.9905. Min Act: -0.1700
Data Index: 7664439 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.9905. Min Act: -0.1700
Data Index: 6911958 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.9592. Min Act: -0.1700
Data Index: 8116297 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.9905. Min Act: -0.1700
Data Index: 5458676 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.9592. Min Act: -0.1700
Data Index: 3812240 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.9280. Min Act: -0.1700
Data Index: 2160967 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.9592. Min Act: -0.1700
Data Index: 4973262 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.9592. Min Act: -0.1700
Data Index: 2155785 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.9280. Min Act: -0.1700
Data Index: 4662139 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.9280. Min Act: -0.1700
Data Index: 5213746 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.9592. Min Act: -0.1700
Data Index: 5352083 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19