Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2016 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6021. Min Range: -6.6021
Max Act: 6.6021. Min Act: -0.1700
Data Index: 2094714 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6021. Min Range: -6.6021
Max Act: 6.4459. Min Act: -0.1700
Data Index: 7856368 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6021. Min Range: -6.6021
Max Act: 6.4146. Min Act: -0.1700
Data Index: 3443426 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6021. Min Range: -6.6021
Max Act: 6.3834. Min Act: -0.1700
Data Index: 2516126 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6021. Min Range: -6.6021
Max Act: 6.4146. Min Act: -0.1700
Data Index: 4474227 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6021. Min Range: -6.6021
Max Act: 6.2584. Min Act: -0.1700
Data Index: 811094 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6021. Min Range: -6.6021
Max Act: 6.2896. Min Act: -0.1700
Data Index: 8798203 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6021. Min Range: -6.6021
Max Act: 6.2584. Min Act: -0.1700
Data Index: 8595316 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6021. Min Range: -6.6021
Max Act: 6.2584. Min Act: -0.1700
Data Index: 8392370 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6021. Min Range: -6.6021
Max Act: 6.1959. Min Act: -0.1700
Data Index: 7695873 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6021. Min Range: -6.6021
Max Act: 6.1646. Min Act: -0.1700
Data Index: 3645640 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6021. Min Range: -6.6021
Max Act: 6.2271. Min Act: -0.1700
Data Index: 295191 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6021. Min Range: -6.6021
Max Act: 6.1959. Min Act: -0.1700
Data Index: 2482054 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6021. Min Range: -6.6021
Max Act: 6.1334. Min Act: -0.1700
Data Index: 7521275 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6021. Min Range: -6.6021
Max Act: 6.1021. Min Act: -0.1700
Data Index: 2294520 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6021. Min Range: -6.6021
Max Act: 6.0396. Min Act: -0.1700
Data Index: 5037437 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6021. Min Range: -6.6021
Max Act: 6.0396. Min Act: -0.1700
Data Index: 4996653 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6021. Min Range: -6.6021
Max Act: 6.0396. Min Act: -0.1700
Data Index: 7014306 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6021. Min Range: -6.6021
Max Act: 6.0084. Min Act: -0.1700
Data Index: 2668288 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6021. Min Range: -6.6021
Max Act: 6.0084. Min Act: -0.1700
Data Index: 7213826 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19