Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4622 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0229. Min Range: -10.0229
Max Act: 10.0229. Min Act: -0.1700
Data Index: 6376159 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0229. Min Range: -10.0229
Max Act: 10.0229. Min Act: -0.1700
Data Index: 4734182 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0229. Min Range: -10.0229
Max Act: 9.9604. Min Act: -0.1700
Data Index: 7083608 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0229. Min Range: -10.0229
Max Act: 9.9604. Min Act: -0.1700
Data Index: 7083607 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0229. Min Range: -10.0229
Max Act: 9.8979. Min Act: -0.1700
Data Index: 5201742 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0229. Min Range: -10.0229
Max Act: 9.8354. Min Act: -0.1700
Data Index: 5824279 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0229. Min Range: -10.0229
Max Act: 9.8354. Min Act: -0.1700
Data Index: 7799181 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0229. Min Range: -10.0229
Max Act: 9.7729. Min Act: -0.1700
Data Index: 683073 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0229. Min Range: -10.0229
Max Act: 9.7104. Min Act: -0.1700
Data Index: 2458213 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0229. Min Range: -10.0229
Max Act: 9.7104. Min Act: -0.1700
Data Index: 127354 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0229. Min Range: -10.0229
Max Act: 9.7104. Min Act: -0.1700
Data Index: 8704077 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0229. Min Range: -10.0229
Max Act: 9.7104. Min Act: -0.1700
Data Index: 5338016 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0229. Min Range: -10.0229
Max Act: 9.5854. Min Act: -0.1700
Data Index: 4425378 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0229. Min Range: -10.0229
Max Act: 9.5854. Min Act: -0.1700
Data Index: 845597 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0229. Min Range: -10.0229
Max Act: 9.5854. Min Act: -0.1700
Data Index: 6515358 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0229. Min Range: -10.0229
Max Act: 9.6479. Min Act: -0.1700
Data Index: 6513309 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0229. Min Range: -10.0229
Max Act: 9.5854. Min Act: -0.1700
Data Index: 3732663 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0229. Min Range: -10.0229
Max Act: 9.5229. Min Act: -0.1700
Data Index: 523673 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0229. Min Range: -10.0229
Max Act: 9.4604. Min Act: -0.1700
Data Index: 3502339 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0229. Min Range: -10.0229
Max Act: 9.5229. Min Act: -0.1700
Data Index: 7973580 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19