Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0316. Min Range: -8.0316
Max Act: 8.0316. Min Act: -0.1700
Data Index: 189142 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0316. Min Range: -8.0316
Max Act: 7.9691. Min Act: -0.1700
Data Index: 4480446 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0316. Min Range: -8.0316
Max Act: 7.8128. Min Act: -0.1700
Data Index: 8133 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0316. Min Range: -8.0316
Max Act: 7.7503. Min Act: -0.1700
Data Index: 7138359 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0316. Min Range: -8.0316
Max Act: 7.7503. Min Act: -0.1700
Data Index: 7760384 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0316. Min Range: -8.0316
Max Act: 7.6878. Min Act: -0.1700
Data Index: 6475501 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0316. Min Range: -8.0316
Max Act: 7.6566. Min Act: -0.1700
Data Index: 4528935 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0316. Min Range: -8.0316
Max Act: 7.6566. Min Act: -0.1700
Data Index: 7914421 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0316. Min Range: -8.0316
Max Act: 7.5316. Min Act: -0.1700
Data Index: 2409028 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0316. Min Range: -8.0316
Max Act: 7.5316. Min Act: -0.1700
Data Index: 4550031 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0316. Min Range: -8.0316
Max Act: 7.5003. Min Act: -0.1700
Data Index: 781140 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0316. Min Range: -8.0316
Max Act: 7.5003. Min Act: -0.1700
Data Index: 1663088 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0316. Min Range: -8.0316
Max Act: 7.4378. Min Act: -0.1700
Data Index: 3060006 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0316. Min Range: -8.0316
Max Act: 7.3753. Min Act: -0.1700
Data Index: 1426924 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0316. Min Range: -8.0316
Max Act: 7.3128. Min Act: -0.1700
Data Index: 2746694 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0316. Min Range: -8.0316
Max Act: 7.3128. Min Act: -0.1700
Data Index: 5264061 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0316. Min Range: -8.0316
Max Act: 7.2816. Min Act: -0.1700
Data Index: 1676261 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0316. Min Range: -8.0316
Max Act: 7.3128. Min Act: -0.1700
Data Index: 528051 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0316. Min Range: -8.0316
Max Act: 7.3128. Min Act: -0.1700
Data Index: 2338922 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0316. Min Range: -8.0316
Max Act: 7.2816. Min Act: -0.1700
Data Index: 5891607 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19