Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3789 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5097. Min Range: -5.5097
Max Act: 5.5097. Min Act: -0.1700
Data Index: 630339 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5097. Min Range: -5.5097
Max Act: 5.4472. Min Act: -0.1700
Data Index: 3494762 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5097. Min Range: -5.5097
Max Act: 5.4785. Min Act: -0.1700
Data Index: 918679 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5097. Min Range: -5.5097
Max Act: 5.4160. Min Act: -0.1700
Data Index: 3291594 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5097. Min Range: -5.5097
Max Act: 5.4160. Min Act: -0.1700
Data Index: 7150521 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5097. Min Range: -5.5097
Max Act: 5.3535. Min Act: -0.1700
Data Index: 259461 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5097. Min Range: -5.5097
Max Act: 5.1972. Min Act: -0.1700
Data Index: 3640803 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5097. Min Range: -5.5097
Max Act: 5.1035. Min Act: -0.1700
Data Index: 861075 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5097. Min Range: -5.5097
Max Act: 4.9785. Min Act: -0.1700
Data Index: 2910719 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5097. Min Range: -5.5097
Max Act: 4.9472. Min Act: -0.1700
Data Index: 6622692 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5097. Min Range: -5.5097
Max Act: 4.9160. Min Act: -0.1700
Data Index: 2241134 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5097. Min Range: -5.5097
Max Act: 4.9160. Min Act: -0.1700
Data Index: 298564 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5097. Min Range: -5.5097
Max Act: 4.9472. Min Act: -0.1700
Data Index: 8775990 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5097. Min Range: -5.5097
Max Act: 4.9160. Min Act: -0.1700
Data Index: 8326583 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5097. Min Range: -5.5097
Max Act: 4.9160. Min Act: -0.1700
Data Index: 2298047 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5097. Min Range: -5.5097
Max Act: 4.9160. Min Act: -0.1700
Data Index: 2770983 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5097. Min Range: -5.5097
Max Act: 4.8847. Min Act: -0.1700
Data Index: 7254092 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5097. Min Range: -5.5097
Max Act: 4.8847. Min Act: -0.1700
Data Index: 7305169 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5097. Min Range: -5.5097
Max Act: 4.8847. Min Act: -0.1700
Data Index: 4179369 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5097. Min Range: -5.5097
Max Act: 4.8535. Min Act: -0.1700
Data Index: 3204972 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19