Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5274 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.4025. Min Act: -0.1700
Data Index: 292153 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.2150. Min Act: -0.1700
Data Index: 8303359 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.9962. Min Act: -0.1700
Data Index: 8358443 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.9962. Min Act: -0.1700
Data Index: 2426831 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.8400. Min Act: -0.1700
Data Index: 8209332 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.8400. Min Act: -0.1700
Data Index: 1246907 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.8400. Min Act: -0.1700
Data Index: 8303352 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.7462. Min Act: -0.1700
Data Index: 8358450 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.7150. Min Act: -0.1700
Data Index: 4625009 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.7150. Min Act: -0.1700
Data Index: 5796951 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.6837. Min Act: -0.1700
Data Index: 6307371 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.6837. Min Act: -0.1700
Data Index: 7119380 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.6525. Min Act: -0.1700
Data Index: 6307370 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.6212. Min Act: -0.1700
Data Index: 6516250 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.6212. Min Act: -0.1700
Data Index: 294480 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.6525. Min Act: -0.1700
Data Index: 2108053 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.5900. Min Act: -0.1700
Data Index: 5796953 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.5900. Min Act: -0.1700
Data Index: 4768173 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.5900. Min Act: -0.1700
Data Index: 1558967 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.5900. Min Act: -0.1700
Data Index: 5986524 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19