Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1850 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7651. Min Range: -1.7651
Max Act: 1.7651. Min Act: -0.1700
Data Index: 7226660 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7651. Min Range: -1.7651
Max Act: 1.7219. Min Act: -0.1700
Data Index: 1466523 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7651. Min Range: -1.7651
Max Act: 1.7046. Min Act: -0.1700
Data Index: 8304327 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7651. Min Range: -1.7651
Max Act: 1.6959. Min Act: -0.1700
Data Index: 5172423 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7651. Min Range: -1.7651
Max Act: 1.6959. Min Act: -0.1700
Data Index: 83673 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7651. Min Range: -1.7651
Max Act: 1.6785. Min Act: -0.1700
Data Index: 1602293 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7651. Min Range: -1.7651
Max Act: 1.6872. Min Act: -0.1700
Data Index: 8125960 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7651. Min Range: -1.7651
Max Act: 1.6785. Min Act: -0.1700
Data Index: 8702049 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7651. Min Range: -1.7651
Max Act: 1.6872. Min Act: -0.1700
Data Index: 3093513 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7651. Min Range: -1.7651
Max Act: 1.6785. Min Act: -0.1700
Data Index: 7124098 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7651. Min Range: -1.7651
Max Act: 1.6785. Min Act: -0.1699
Data Index: 1590949 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7651. Min Range: -1.7651
Max Act: 1.6611. Min Act: -0.1700
Data Index: 8263590 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7651. Min Range: -1.7651
Max Act: 1.6698. Min Act: -0.1700
Data Index: 4670244 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7651. Min Range: -1.7651
Max Act: 1.6437. Min Act: -0.1700
Data Index: 5357133 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7651. Min Range: -1.7651
Max Act: 1.6611. Min Act: -0.1700
Data Index: 5244078 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7651. Min Range: -1.7651
Max Act: 1.6524. Min Act: -0.1700
Data Index: 4542538 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7651. Min Range: -1.7651
Max Act: 1.6611. Min Act: -0.1700
Data Index: 2014878 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7651. Min Range: -1.7651
Max Act: 1.6524. Min Act: -0.1700
Data Index: 3424148 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7651. Min Range: -1.7651
Max Act: 1.6437. Min Act: -0.1700
Data Index: 2584664 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7651. Min Range: -1.7651
Max Act: 1.6437. Min Act: -0.1700
Data Index: 3138887 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19