Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1793 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4733. Min Range: -5.4733
Max Act: 5.4733. Min Act: -0.1700
Data Index: 2501454 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4733. Min Range: -5.4733
Max Act: 5.4733. Min Act: -0.1700
Data Index: 152796 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4733. Min Range: -5.4733
Max Act: 5.4108. Min Act: -0.1700
Data Index: 8783924 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4733. Min Range: -5.4733
Max Act: 5.4108. Min Act: -0.1700
Data Index: 130457 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4733. Min Range: -5.4733
Max Act: 5.3795. Min Act: -0.1700
Data Index: 7235141 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4733. Min Range: -5.4733
Max Act: 5.3483. Min Act: -0.1700
Data Index: 5452283 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4733. Min Range: -5.4733
Max Act: 5.3170. Min Act: -0.1700
Data Index: 6265980 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4733. Min Range: -5.4733
Max Act: 5.2858. Min Act: -0.1700
Data Index: 7564886 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4733. Min Range: -5.4733
Max Act: 5.2858. Min Act: -0.1700
Data Index: 1211755 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4733. Min Range: -5.4733
Max Act: 5.2545. Min Act: -0.1700
Data Index: 1808301 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4733. Min Range: -5.4733
Max Act: 5.2545. Min Act: -0.1700
Data Index: 5022579 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4733. Min Range: -5.4733
Max Act: 5.2233. Min Act: -0.1700
Data Index: 6928335 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4733. Min Range: -5.4733
Max Act: 5.1920. Min Act: -0.1700
Data Index: 6074137 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4733. Min Range: -5.4733
Max Act: 5.1920. Min Act: -0.1700
Data Index: 165648 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4733. Min Range: -5.4733
Max Act: 5.1920. Min Act: -0.1700
Data Index: 4044782 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4733. Min Range: -5.4733
Max Act: 5.1920. Min Act: -0.1700
Data Index: 2564375 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4733. Min Range: -5.4733
Max Act: 5.1608. Min Act: -0.1700
Data Index: 1027586 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4733. Min Range: -5.4733
Max Act: 5.1920. Min Act: -0.1700
Data Index: 206107 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4733. Min Range: -5.4733
Max Act: 5.1920. Min Act: -0.1700
Data Index: 3603236 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4733. Min Range: -5.4733
Max Act: 5.1920. Min Act: -0.1700
Data Index: 4049070 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19