Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 802 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1740. Min Range: -6.1740
Max Act: 6.1740. Min Act: -0.1700
Data Index: 4360751 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1740. Min Range: -6.1740
Max Act: 6.1427. Min Act: -0.1700
Data Index: 7361349 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.9865. Min Act: -0.1700
Data Index: 155524 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.8927. Min Act: -0.1700
Data Index: 4285060 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.9240. Min Act: -0.1700
Data Index: 6145753 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.9240. Min Act: -0.1700
Data Index: 5721405 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.8927. Min Act: -0.1700
Data Index: 1119435 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.8615. Min Act: -0.1700
Data Index: 4029485 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.8927. Min Act: -0.1700
Data Index: 568097 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.8302. Min Act: -0.1700
Data Index: 5448769 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.8302. Min Act: -0.1700
Data Index: 5066420 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.8302. Min Act: -0.1700
Data Index: 8758293 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.8302. Min Act: -0.1700
Data Index: 1245952 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.8302. Min Act: -0.1700
Data Index: 6364448 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.7990. Min Act: -0.1700
Data Index: 8625895 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.7990. Min Act: -0.1700
Data Index: 7658351 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.7990. Min Act: -0.1700
Data Index: 4041534 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.7990. Min Act: -0.1700
Data Index: 4740181 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.7677. Min Act: -0.1700
Data Index: 1626658 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.7677. Min Act: -0.1700
Data Index: 2532125 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19