Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3190 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9768. Min Range: -5.9768
Max Act: 5.9768. Min Act: -0.1700
Data Index: 512032 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9768. Min Range: -5.9768
Max Act: 5.5706. Min Act: -0.1700
Data Index: 4261187 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9768. Min Range: -5.9768
Max Act: 5.5393. Min Act: -0.1700
Data Index: 2146529 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9768. Min Range: -5.9768
Max Act: 5.3831. Min Act: -0.1700
Data Index: 2103908 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9768. Min Range: -5.9768
Max Act: 5.3518. Min Act: -0.1700
Data Index: 5491201 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9768. Min Range: -5.9768
Max Act: 5.3518. Min Act: -0.1700
Data Index: 8547248 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9768. Min Range: -5.9768
Max Act: 5.3206. Min Act: -0.1700
Data Index: 8232839 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9768. Min Range: -5.9768
Max Act: 5.3206. Min Act: -0.1700
Data Index: 2014910 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9768. Min Range: -5.9768
Max Act: 5.2581. Min Act: -0.1700
Data Index: 499204 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9768. Min Range: -5.9768
Max Act: 5.2893. Min Act: -0.1700
Data Index: 8786216 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9768. Min Range: -5.9768
Max Act: 5.2581. Min Act: -0.1700
Data Index: 5948212 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9768. Min Range: -5.9768
Max Act: 5.2893. Min Act: -0.1700
Data Index: 5623696 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9768. Min Range: -5.9768
Max Act: 5.2581. Min Act: -0.1700
Data Index: 8105090 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9768. Min Range: -5.9768
Max Act: 5.2581. Min Act: -0.1700
Data Index: 124266 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9768. Min Range: -5.9768
Max Act: 5.2268. Min Act: -0.1700
Data Index: 4842350 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9768. Min Range: -5.9768
Max Act: 5.2268. Min Act: -0.1700
Data Index: 5407063 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9768. Min Range: -5.9768
Max Act: 5.1956. Min Act: -0.1700
Data Index: 6714640 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9768. Min Range: -5.9768
Max Act: 5.1956. Min Act: -0.1700
Data Index: 4926788 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9768. Min Range: -5.9768
Max Act: 5.1956. Min Act: -0.1700
Data Index: 8166140 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9768. Min Range: -5.9768
Max Act: 5.1643. Min Act: -0.1700
Data Index: 4842582 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19