Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3131 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1810. Min Range: -9.1810
Max Act: 9.1810. Min Act: -0.1700
Data Index: 8716975 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1810. Min Range: -9.1810
Max Act: 9.0560. Min Act: -0.1700
Data Index: 1319847 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1810. Min Range: -9.1810
Max Act: 8.9310. Min Act: -0.1700
Data Index: 4181171 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1810. Min Range: -9.1810
Max Act: 8.6810. Min Act: -0.1700
Data Index: 8280952 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1810. Min Range: -9.1810
Max Act: 8.6185. Min Act: -0.1700
Data Index: 7273222 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1810. Min Range: -9.1810
Max Act: 8.5560. Min Act: -0.1700
Data Index: 7526868 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1810. Min Range: -9.1810
Max Act: 8.5560. Min Act: -0.1700
Data Index: 6481211 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1810. Min Range: -9.1810
Max Act: 8.4935. Min Act: -0.1700
Data Index: 7421822 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1810. Min Range: -9.1810
Max Act: 8.4310. Min Act: -0.1700
Data Index: 8301554 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1810. Min Range: -9.1810
Max Act: 8.4310. Min Act: -0.1700
Data Index: 8235475 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1810. Min Range: -9.1810
Max Act: 8.4310. Min Act: -0.1700
Data Index: 7442540 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1810. Min Range: -9.1810
Max Act: 8.3685. Min Act: -0.1700
Data Index: 2082462 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1810. Min Range: -9.1810
Max Act: 8.3685. Min Act: -0.1700
Data Index: 5800152 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1810. Min Range: -9.1810
Max Act: 8.3685. Min Act: -0.1700
Data Index: 5358304 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1810. Min Range: -9.1810
Max Act: 8.3685. Min Act: -0.1700
Data Index: 3172567 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1810. Min Range: -9.1810
Max Act: 8.3060. Min Act: -0.1700
Data Index: 6663696 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1810. Min Range: -9.1810
Max Act: 8.3060. Min Act: -0.1700
Data Index: 7451891 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1810. Min Range: -9.1810
Max Act: 8.3060. Min Act: -0.1700
Data Index: 6461190 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1810. Min Range: -9.1810
Max Act: 8.3060. Min Act: -0.1700
Data Index: 7786324 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1810. Min Range: -9.1810
Max Act: 8.3060. Min Act: -0.1700
Data Index: 7093448 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19