Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3163 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0371. Min Range: -5.0371
Max Act: 5.0371. Min Act: -0.1700
Data Index: 5662684 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0371. Min Range: -5.0371
Max Act: 4.8809. Min Act: -0.1700
Data Index: 3196704 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0371. Min Range: -5.0371
Max Act: 4.7246. Min Act: -0.1700
Data Index: 4385829 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0371. Min Range: -5.0371
Max Act: 4.6621. Min Act: -0.1700
Data Index: 3086667 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0371. Min Range: -5.0371
Max Act: 4.6621. Min Act: -0.1700
Data Index: 6730657 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0371. Min Range: -5.0371
Max Act: 4.6621. Min Act: -0.1700
Data Index: 1896418 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0371. Min Range: -5.0371
Max Act: 4.6309. Min Act: -0.1700
Data Index: 2826185 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0371. Min Range: -5.0371
Max Act: 4.6621. Min Act: -0.1700
Data Index: 7528418 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0371. Min Range: -5.0371
Max Act: 4.5996. Min Act: -0.1700
Data Index: 5434451 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0371. Min Range: -5.0371
Max Act: 4.5996. Min Act: -0.1700
Data Index: 2953973 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0371. Min Range: -5.0371
Max Act: 4.5684. Min Act: -0.1700
Data Index: 512669 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0371. Min Range: -5.0371
Max Act: 4.5684. Min Act: -0.1700
Data Index: 4236812 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0371. Min Range: -5.0371
Max Act: 4.5684. Min Act: -0.1700
Data Index: 5047277 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0371. Min Range: -5.0371
Max Act: 4.5684. Min Act: -0.1700
Data Index: 8255949 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0371. Min Range: -5.0371
Max Act: 4.5371. Min Act: -0.1700
Data Index: 1323207 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0371. Min Range: -5.0371
Max Act: 4.5059. Min Act: -0.1700
Data Index: 6538040 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0371. Min Range: -5.0371
Max Act: 4.5371. Min Act: -0.1700
Data Index: 5405537 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0371. Min Range: -5.0371
Max Act: 4.5059. Min Act: -0.1700
Data Index: 230816 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0371. Min Range: -5.0371
Max Act: 4.5059. Min Act: -0.1700
Data Index: 5654097 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0371. Min Range: -5.0371
Max Act: 4.5371. Min Act: -0.1700
Data Index: 1378383 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19