Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2593 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3899. Min Range: -4.3899
Max Act: 4.3899. Min Act: -0.1700
Data Index: 7080002 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3899. Min Range: -4.3899
Max Act: 4.3586. Min Act: -0.1700
Data Index: 5345805 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3899. Min Range: -4.3899
Max Act: 4.3586. Min Act: -0.1700
Data Index: 6092875 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3899. Min Range: -4.3899
Max Act: 4.3899. Min Act: -0.1700
Data Index: 7744889 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3899. Min Range: -4.3899
Max Act: 4.2649. Min Act: -0.1700
Data Index: 8293688 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3899. Min Range: -4.3899
Max Act: 4.2336. Min Act: -0.1700
Data Index: 6389506 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3899. Min Range: -4.3899
Max Act: 4.2023. Min Act: -0.1700
Data Index: 7703690 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3899. Min Range: -4.3899
Max Act: 4.2023. Min Act: -0.1700
Data Index: 7355198 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3899. Min Range: -4.3899
Max Act: 4.2023. Min Act: -0.1700
Data Index: 5332583 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3899. Min Range: -4.3899
Max Act: 4.2023. Min Act: -0.1700
Data Index: 7354376 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3899. Min Range: -4.3899
Max Act: 4.2336. Min Act: -0.1700
Data Index: 3161855 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3899. Min Range: -4.3899
Max Act: 4.1711. Min Act: -0.1700
Data Index: 493141 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3899. Min Range: -4.3899
Max Act: 4.1711. Min Act: -0.1700
Data Index: 4733681 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3899. Min Range: -4.3899
Max Act: 4.1711. Min Act: -0.1700
Data Index: 1607014 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3899. Min Range: -4.3899
Max Act: 4.1711. Min Act: -0.1700
Data Index: 6335895 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3899. Min Range: -4.3899
Max Act: 4.1711. Min Act: -0.1700
Data Index: 5744482 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3899. Min Range: -4.3899
Max Act: 4.1711. Min Act: -0.1700
Data Index: 304312 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3899. Min Range: -4.3899
Max Act: 4.1711. Min Act: -0.1700
Data Index: 4705722 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3899. Min Range: -4.3899
Max Act: 4.1398. Min Act: -0.1700
Data Index: 5535831 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3899. Min Range: -4.3899
Max Act: 4.1398. Min Act: -0.1700
Data Index: 540899 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19