Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2146 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0794. Min Range: -5.0794
Max Act: 5.0794. Min Act: -0.1700
Data Index: 743734 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0794. Min Range: -5.0794
Max Act: 4.9231. Min Act: -0.1700
Data Index: 3141655 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0794. Min Range: -5.0794
Max Act: 4.8294. Min Act: -0.1700
Data Index: 293953 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0794. Min Range: -5.0794
Max Act: 4.7981. Min Act: -0.1700
Data Index: 3676880 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0794. Min Range: -5.0794
Max Act: 4.7981. Min Act: -0.1700
Data Index: 8721168 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0794. Min Range: -5.0794
Max Act: 4.7356. Min Act: -0.1700
Data Index: 6212155 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0794. Min Range: -5.0794
Max Act: 4.7044. Min Act: -0.1700
Data Index: 6981258 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0794. Min Range: -5.0794
Max Act: 4.7044. Min Act: -0.1700
Data Index: 243759 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0794. Min Range: -5.0794
Max Act: 4.7044. Min Act: -0.1700
Data Index: 1416924 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0794. Min Range: -5.0794
Max Act: 4.7044. Min Act: -0.1700
Data Index: 218909 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0794. Min Range: -5.0794
Max Act: 4.6731. Min Act: -0.1700
Data Index: 4161891 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0794. Min Range: -5.0794
Max Act: 4.6419. Min Act: -0.1700
Data Index: 4015626 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0794. Min Range: -5.0794
Max Act: 4.6106. Min Act: -0.1700
Data Index: 2959720 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0794. Min Range: -5.0794
Max Act: 4.6106. Min Act: -0.1700
Data Index: 4597062 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0794. Min Range: -5.0794
Max Act: 4.5794. Min Act: -0.1700
Data Index: 4606472 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0794. Min Range: -5.0794
Max Act: 4.5794. Min Act: -0.1700
Data Index: 8479185 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0794. Min Range: -5.0794
Max Act: 4.5794. Min Act: -0.1700
Data Index: 8057729 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0794. Min Range: -5.0794
Max Act: 4.5481. Min Act: -0.1700
Data Index: 5179321 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0794. Min Range: -5.0794
Max Act: 4.5794. Min Act: -0.1700
Data Index: 4951190 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0794. Min Range: -5.0794
Max Act: 4.5794. Min Act: -0.1700
Data Index: 2474433 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19