Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 914 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.4838. Min Act: -0.1700
Data Index: 3514006 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.4526. Min Act: -0.1700
Data Index: 6294429 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.3276. Min Act: -0.1700
Data Index: 6338836 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.2963. Min Act: -0.1700
Data Index: 1921751 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.2963. Min Act: -0.1700
Data Index: 1542687 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.2963. Min Act: -0.1700
Data Index: 6814587 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.2338. Min Act: -0.1700
Data Index: 1424168 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.2338. Min Act: -0.1700
Data Index: 7043970 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.1713. Min Act: -0.1700
Data Index: 3318452 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.1713. Min Act: -0.1700
Data Index: 4504712 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.1401. Min Act: -0.1700
Data Index: 7419596 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.1088. Min Act: -0.1700
Data Index: 8227514 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.1088. Min Act: -0.1700
Data Index: 5460393 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.1088. Min Act: -0.1700
Data Index: 6338837 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.1088. Min Act: -0.1700
Data Index: 3957520 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.0776. Min Act: -0.1700
Data Index: 1797976 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.0776. Min Act: -0.1700
Data Index: 6577022 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.0776. Min Act: -0.1700
Data Index: 7844024 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.0463. Min Act: -0.1700
Data Index: 5357597 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4838. Min Range: -5.4838
Max Act: 5.0463. Min Act: -0.1700
Data Index: 4695124 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19