Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1072 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8863. Min Range: -2.8863
Max Act: 2.8863. Min Act: -0.1700
Data Index: 7837326 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8863. Min Range: -2.8863
Max Act: 2.8705. Min Act: -0.1700
Data Index: 7492903 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8863. Min Range: -2.8863
Max Act: 2.8546. Min Act: -0.1700
Data Index: 7175136 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8863. Min Range: -2.8863
Max Act: 2.7910. Min Act: -0.1700
Data Index: 4038676 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8863. Min Range: -2.8863
Max Act: 2.7591. Min Act: -0.1700
Data Index: 4601685 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8863. Min Range: -2.8863
Max Act: 2.7591. Min Act: -0.1700
Data Index: 2248528 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8863. Min Range: -2.8863
Max Act: 2.7271. Min Act: -0.1700
Data Index: 6920675 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8863. Min Range: -2.8863
Max Act: 2.7111. Min Act: -0.1700
Data Index: 837641 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8863. Min Range: -2.8863
Max Act: 2.6951. Min Act: -0.1700
Data Index: 8140686 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8863. Min Range: -2.8863
Max Act: 2.6951. Min Act: -0.1700
Data Index: 5041985 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8863. Min Range: -2.8863
Max Act: 2.6951. Min Act: -0.1700
Data Index: 7260647 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8863. Min Range: -2.8863
Max Act: 2.6791. Min Act: -0.1700
Data Index: 7350850 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8863. Min Range: -2.8863
Max Act: 2.6791. Min Act: -0.1700
Data Index: 7081058 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8863. Min Range: -2.8863
Max Act: 2.6791. Min Act: -0.1700
Data Index: 4116589 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8863. Min Range: -2.8863
Max Act: 2.6791. Min Act: -0.1700
Data Index: 3576203 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8863. Min Range: -2.8863
Max Act: 2.6791. Min Act: -0.1700
Data Index: 6467072 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8863. Min Range: -2.8863
Max Act: 2.6631. Min Act: -0.1700
Data Index: 6076175 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8863. Min Range: -2.8863
Max Act: 2.6791. Min Act: -0.1700
Data Index: 3344574 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8863. Min Range: -2.8863
Max Act: 2.6791. Min Act: -0.1700
Data Index: 2750317 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8863. Min Range: -2.8863
Max Act: 2.6631. Min Act: -0.1700
Data Index: 1235945 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19