Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 453 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1234. Min Range: -6.1234
Max Act: 6.1234. Min Act: -0.1700
Data Index: 4777145 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1234. Min Range: -6.1234
Max Act: 5.9046. Min Act: -0.1700
Data Index: 4335100 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1234. Min Range: -6.1234
Max Act: 5.8421. Min Act: -0.1700
Data Index: 2279495 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1234. Min Range: -6.1234
Max Act: 5.8109. Min Act: -0.1700
Data Index: 2471559 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1234. Min Range: -6.1234
Max Act: 5.7796. Min Act: -0.1700
Data Index: 7540152 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1234. Min Range: -6.1234
Max Act: 5.7796. Min Act: -0.1700
Data Index: 774168 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1234. Min Range: -6.1234
Max Act: 5.7484. Min Act: -0.1700
Data Index: 7132005 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1234. Min Range: -6.1234
Max Act: 5.7171. Min Act: -0.1700
Data Index: 6906126 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1234. Min Range: -6.1234
Max Act: 5.7484. Min Act: -0.1700
Data Index: 2661220 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1234. Min Range: -6.1234
Max Act: 5.6859. Min Act: -0.1700
Data Index: 3141681 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1234. Min Range: -6.1234
Max Act: 5.6546. Min Act: -0.1700
Data Index: 5425878 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1234. Min Range: -6.1234
Max Act: 5.7171. Min Act: -0.1700
Data Index: 512813 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1234. Min Range: -6.1234
Max Act: 5.6546. Min Act: -0.1700
Data Index: 1006117 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1234. Min Range: -6.1234
Max Act: 5.6546. Min Act: -0.1700
Data Index: 7314080 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1234. Min Range: -6.1234
Max Act: 5.6859. Min Act: -0.1700
Data Index: 7516321 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1234. Min Range: -6.1234
Max Act: 5.6234. Min Act: -0.1700
Data Index: 4162621 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1234. Min Range: -6.1234
Max Act: 5.6546. Min Act: -0.1700
Data Index: 2793497 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1234. Min Range: -6.1234
Max Act: 5.6546. Min Act: -0.1700
Data Index: 8281926 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1234. Min Range: -6.1234
Max Act: 5.6546. Min Act: -0.1700
Data Index: 286525 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1234. Min Range: -6.1234
Max Act: 5.6546. Min Act: -0.1700
Data Index: 6575647 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19