Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4015 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3021. Min Range: -6.3021
Max Act: 6.3021. Min Act: -0.1700
Data Index: 1248027 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3021. Min Range: -6.3021
Max Act: 6.3021. Min Act: -0.1700
Data Index: 2276746 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3021. Min Range: -6.3021
Max Act: 6.2709. Min Act: -0.1700
Data Index: 2878347 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3021. Min Range: -6.3021
Max Act: 6.2396. Min Act: -0.1700
Data Index: 4897875 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3021. Min Range: -6.3021
Max Act: 6.2396. Min Act: -0.1700
Data Index: 3073034 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3021. Min Range: -6.3021
Max Act: 6.2396. Min Act: -0.1700
Data Index: 3546674 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3021. Min Range: -6.3021
Max Act: 6.2084. Min Act: -0.1700
Data Index: 6148330 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3021. Min Range: -6.3021
Max Act: 6.1459. Min Act: -0.1700
Data Index: 7080185 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3021. Min Range: -6.3021
Max Act: 6.1146. Min Act: -0.1700
Data Index: 2276745 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3021. Min Range: -6.3021
Max Act: 6.1146. Min Act: -0.1700
Data Index: 8704852 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3021. Min Range: -6.3021
Max Act: 6.1146. Min Act: -0.1700
Data Index: 4532592 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3021. Min Range: -6.3021
Max Act: 6.0834. Min Act: -0.1700
Data Index: 2363866 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3021. Min Range: -6.3021
Max Act: 6.0834. Min Act: -0.1700
Data Index: 8798041 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3021. Min Range: -6.3021
Max Act: 6.0209. Min Act: -0.1700
Data Index: 6113770 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3021. Min Range: -6.3021
Max Act: 6.0834. Min Act: -0.1700
Data Index: 1392757 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3021. Min Range: -6.3021
Max Act: 6.0521. Min Act: -0.1700
Data Index: 4901773 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3021. Min Range: -6.3021
Max Act: 6.0209. Min Act: -0.1700
Data Index: 3702775 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3021. Min Range: -6.3021
Max Act: 6.0209. Min Act: -0.1700
Data Index: 4986008 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3021. Min Range: -6.3021
Max Act: 5.9896. Min Act: -0.1700
Data Index: 8496473 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3021. Min Range: -6.3021
Max Act: 5.9896. Min Act: -0.1700
Data Index: 3822960 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19