Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 628 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.5386. Min Act: -0.1700
Data Index: 3426335 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.5074. Min Act: -0.1700
Data Index: 311710 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.4761. Min Act: -0.1700
Data Index: 5393145 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.3511. Min Act: -0.1700
Data Index: 8224703 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.3511. Min Act: -0.1700
Data Index: 5374723 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.3199. Min Act: -0.1700
Data Index: 4039316 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.3199. Min Act: -0.1700
Data Index: 4096504 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.3199. Min Act: -0.1700
Data Index: 8585657 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.2886. Min Act: -0.1700
Data Index: 2384640 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.2886. Min Act: -0.1700
Data Index: 3756826 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.2886. Min Act: -0.1700
Data Index: 3470310 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.2886. Min Act: -0.1700
Data Index: 8359518 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.2574. Min Act: -0.1700
Data Index: 3364288 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.2574. Min Act: -0.1700
Data Index: 5512182 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.2261. Min Act: -0.1700
Data Index: 5900656 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.2261. Min Act: -0.1700
Data Index: 3707827 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.2261. Min Act: -0.1700
Data Index: 4326135 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.1949. Min Act: -0.1700
Data Index: 5568460 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.1949. Min Act: -0.1700
Data Index: 2180103 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.1636. Min Act: -0.1700
Data Index: 2710678 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19