Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 10 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0178. Min Range: -5.0178
Max Act: 5.0178. Min Act: -0.1700
Data Index: 7431430 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0178. Min Range: -5.0178
Max Act: 4.9241. Min Act: -0.1700
Data Index: 2690728 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0178. Min Range: -5.0178
Max Act: 4.8616. Min Act: -0.1700
Data Index: 8500000 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0178. Min Range: -5.0178
Max Act: 4.8303. Min Act: -0.1700
Data Index: 7022569 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0178. Min Range: -5.0178
Max Act: 4.7678. Min Act: -0.1700
Data Index: 8038777 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0178. Min Range: -5.0178
Max Act: 4.6428. Min Act: -0.1700
Data Index: 5790181 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0178. Min Range: -5.0178
Max Act: 4.6428. Min Act: -0.1700
Data Index: 6838456 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0178. Min Range: -5.0178
Max Act: 4.5803. Min Act: -0.1700
Data Index: 3568148 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0178. Min Range: -5.0178
Max Act: 4.6116. Min Act: -0.1700
Data Index: 4291443 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0178. Min Range: -5.0178
Max Act: 4.6116. Min Act: -0.1700
Data Index: 7867002 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0178. Min Range: -5.0178
Max Act: 4.6116. Min Act: -0.1700
Data Index: 2871551 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0178. Min Range: -5.0178
Max Act: 4.6116. Min Act: -0.1700
Data Index: 6207490 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0178. Min Range: -5.0178
Max Act: 4.5803. Min Act: -0.1700
Data Index: 1658817 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0178. Min Range: -5.0178
Max Act: 4.5803. Min Act: -0.1700
Data Index: 1833085 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0178. Min Range: -5.0178
Max Act: 4.5803. Min Act: -0.1700
Data Index: 7200185 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0178. Min Range: -5.0178
Max Act: 4.5803. Min Act: -0.1700
Data Index: 3901216 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0178. Min Range: -5.0178
Max Act: 4.5803. Min Act: -0.1700
Data Index: 8213173 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0178. Min Range: -5.0178
Max Act: 4.5803. Min Act: -0.1700
Data Index: 692308 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0178. Min Range: -5.0178
Max Act: 4.6116. Min Act: -0.1700
Data Index: 2912609 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0178. Min Range: -5.0178
Max Act: 4.5803. Min Act: -0.1700
Data Index: 3390189 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19