Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5077 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0691. Min Range: -3.0691
Max Act: 3.0691. Min Act: -0.1700
Data Index: 7404709 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0691. Min Range: -3.0691
Max Act: 2.9427. Min Act: -0.1700
Data Index: 6254171 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0691. Min Range: -3.0691
Max Act: 2.8952. Min Act: -0.1700
Data Index: 4079840 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0691. Min Range: -3.0691
Max Act: 2.8634. Min Act: -0.1700
Data Index: 6654713 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0691. Min Range: -3.0691
Max Act: 2.8634. Min Act: -0.1700
Data Index: 4934256 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0691. Min Range: -3.0691
Max Act: 2.8475. Min Act: -0.1700
Data Index: 8367215 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0691. Min Range: -3.0691
Max Act: 2.7998. Min Act: -0.1700
Data Index: 532372 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0691. Min Range: -3.0691
Max Act: 2.7839. Min Act: -0.1700
Data Index: 6593086 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0691. Min Range: -3.0691
Max Act: 2.7680. Min Act: -0.1700
Data Index: 6164837 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0691. Min Range: -3.0691
Max Act: 2.7520. Min Act: -0.1700
Data Index: 7667936 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0691. Min Range: -3.0691
Max Act: 2.7360. Min Act: -0.1700
Data Index: 5670010 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0691. Min Range: -3.0691
Max Act: 2.7360. Min Act: -0.1700
Data Index: 3943303 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0691. Min Range: -3.0691
Max Act: 2.7201. Min Act: -0.1700
Data Index: 5270827 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0691. Min Range: -3.0691
Max Act: 2.7360. Min Act: -0.1700
Data Index: 5741516 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0691. Min Range: -3.0691
Max Act: 2.7201. Min Act: -0.1700
Data Index: 986356 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0691. Min Range: -3.0691
Max Act: 2.7201. Min Act: -0.1700
Data Index: 8718854 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0691. Min Range: -3.0691
Max Act: 2.7201. Min Act: -0.1700
Data Index: 4764746 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0691. Min Range: -3.0691
Max Act: 2.6881. Min Act: -0.1700
Data Index: 4770355 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0691. Min Range: -3.0691
Max Act: 2.7041. Min Act: -0.1700
Data Index: 2666082 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0691. Min Range: -3.0691
Max Act: 2.7201. Min Act: -0.1700
Data Index: 6693528 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19