Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5075 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.5736. Min Act: -0.1700
Data Index: 814366 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.5111. Min Act: -0.1700
Data Index: 2987765 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.5423. Min Act: -0.1700
Data Index: 1147959 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.5423. Min Act: -0.1700
Data Index: 5804114 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.5111. Min Act: -0.1700
Data Index: 4439799 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.5423. Min Act: -0.1699
Data Index: 7685741 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.5423. Min Act: -0.1700
Data Index: 455658 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.5423. Min Act: -0.1699
Data Index: 5061306 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.5423. Min Act: -0.1700
Data Index: 2542824 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.5111. Min Act: -0.1700
Data Index: 814360 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.4798. Min Act: -0.1700
Data Index: 2326438 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.4798. Min Act: -0.1700
Data Index: 814367 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.4798. Min Act: -0.1699
Data Index: 4399092 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.4798. Min Act: -0.1700
Data Index: 6332437 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.4798. Min Act: -0.1700
Data Index: 8167008 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.4798. Min Act: -0.1700
Data Index: 7519644 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.4798. Min Act: -0.1700
Data Index: 819218 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.4798. Min Act: -0.1700
Data Index: 6678892 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.4486. Min Act: -0.1700
Data Index: 5073491 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.4486. Min Act: -0.1700
Data Index: 5610859 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19