Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5822 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7851. Min Range: -6.7851
Max Act: 6.7851. Min Act: -0.1700
Data Index: 6822153 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7851. Min Range: -6.7851
Max Act: 6.6601. Min Act: -0.1700
Data Index: 616141 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7851. Min Range: -6.7851
Max Act: 6.6288. Min Act: -0.1700
Data Index: 4962664 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7851. Min Range: -6.7851
Max Act: 6.5351. Min Act: -0.1700
Data Index: 2797652 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7851. Min Range: -6.7851
Max Act: 6.5351. Min Act: -0.1700
Data Index: 385265 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7851. Min Range: -6.7851
Max Act: 6.5351. Min Act: -0.1700
Data Index: 2797651 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7851. Min Range: -6.7851
Max Act: 6.5038. Min Act: -0.1700
Data Index: 2736408 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7851. Min Range: -6.7851
Max Act: 6.4413. Min Act: -0.1700
Data Index: 6822158 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7851. Min Range: -6.7851
Max Act: 6.4101. Min Act: -0.1700
Data Index: 607920 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7851. Min Range: -6.7851
Max Act: 6.3476. Min Act: -0.1700
Data Index: 616157 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7851. Min Range: -6.7851
Max Act: 6.3476. Min Act: -0.1700
Data Index: 2736395 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7851. Min Range: -6.7851
Max Act: 6.3163. Min Act: -0.1700
Data Index: 2361107 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7851. Min Range: -6.7851
Max Act: 6.3163. Min Act: -0.1700
Data Index: 616138 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7851. Min Range: -6.7851
Max Act: 6.2851. Min Act: -0.1700
Data Index: 4208199 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7851. Min Range: -6.7851
Max Act: 6.2851. Min Act: -0.1700
Data Index: 4142974 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7851. Min Range: -6.7851
Max Act: 6.2226. Min Act: -0.1700
Data Index: 2844422 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7851. Min Range: -6.7851
Max Act: 6.2226. Min Act: -0.1700
Data Index: 4541232 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7851. Min Range: -6.7851
Max Act: 6.2226. Min Act: -0.1700
Data Index: 8044692 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7851. Min Range: -6.7851
Max Act: 6.2226. Min Act: -0.1700
Data Index: 8484418 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7851. Min Range: -6.7851
Max Act: 6.2226. Min Act: -0.1700
Data Index: 3894144 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19