Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2226 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6696. Min Range: -3.6696
Max Act: 3.6696. Min Act: -0.1700
Data Index: 6541026 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6696. Min Range: -3.6696
Max Act: 3.6384. Min Act: -0.1700
Data Index: 2047915 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6696. Min Range: -3.6696
Max Act: 3.6384. Min Act: -0.1700
Data Index: 4365640 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6696. Min Range: -3.6696
Max Act: 3.6071. Min Act: -0.1700
Data Index: 5469146 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6696. Min Range: -3.6696
Max Act: 3.6071. Min Act: -0.1700
Data Index: 63893 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6696. Min Range: -3.6696
Max Act: 3.6071. Min Act: -0.1700
Data Index: 2193386 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6696. Min Range: -3.6696
Max Act: 3.6071. Min Act: -0.1700
Data Index: 4922352 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6696. Min Range: -3.6696
Max Act: 3.6071. Min Act: -0.1700
Data Index: 6728710 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6696. Min Range: -3.6696
Max Act: 3.5757. Min Act: -0.1700
Data Index: 4934818 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6696. Min Range: -3.6696
Max Act: 3.5757. Min Act: -0.1700
Data Index: 8583701 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6696. Min Range: -3.6696
Max Act: 3.5757. Min Act: -0.1700
Data Index: 2817645 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6696. Min Range: -3.6696
Max Act: 3.5601. Min Act: -0.1700
Data Index: 4086411 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6696. Min Range: -3.6696
Max Act: 3.5601. Min Act: -0.1700
Data Index: 188243 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6696. Min Range: -3.6696
Max Act: 3.5601. Min Act: -0.1700
Data Index: 981574 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6696. Min Range: -3.6696
Max Act: 3.5601. Min Act: -0.1700
Data Index: 7764700 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6696. Min Range: -3.6696
Max Act: 3.5601. Min Act: -0.1700
Data Index: 7232626 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6696. Min Range: -3.6696
Max Act: 3.5601. Min Act: -0.1700
Data Index: 4182721 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6696. Min Range: -3.6696
Max Act: 3.5601. Min Act: -0.1700
Data Index: 2007973 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6696. Min Range: -3.6696
Max Act: 3.5444. Min Act: -0.1700
Data Index: 4489135 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6696. Min Range: -3.6696
Max Act: 3.5444. Min Act: -0.1700
Data Index: 5696819 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19