Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3386 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8797. Min Range: -6.8797
Max Act: 6.8797. Min Act: -0.1700
Data Index: 8499133 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8797. Min Range: -6.8797
Max Act: 6.8172. Min Act: -0.1700
Data Index: 8350566 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8797. Min Range: -6.8797
Max Act: 6.8172. Min Act: -0.1700
Data Index: 5871394 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8797. Min Range: -6.8797
Max Act: 6.7234. Min Act: -0.1700
Data Index: 2710321 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8797. Min Range: -6.8797
Max Act: 6.7234. Min Act: -0.1700
Data Index: 617358 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8797. Min Range: -6.8797
Max Act: 6.7234. Min Act: -0.1700
Data Index: 2739808 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8797. Min Range: -6.8797
Max Act: 6.6297. Min Act: -0.1700
Data Index: 2160447 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8797. Min Range: -6.8797
Max Act: 6.5984. Min Act: -0.1700
Data Index: 1284990 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8797. Min Range: -6.8797
Max Act: 6.5984. Min Act: -0.1700
Data Index: 7405025 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8797. Min Range: -6.8797
Max Act: 6.5984. Min Act: -0.1700
Data Index: 2160448 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8797. Min Range: -6.8797
Max Act: 6.5672. Min Act: -0.1700
Data Index: 6599225 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8797. Min Range: -6.8797
Max Act: 6.6297. Min Act: -0.1700
Data Index: 4515115 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8797. Min Range: -6.8797
Max Act: 6.5672. Min Act: -0.1700
Data Index: 4971060 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8797. Min Range: -6.8797
Max Act: 6.5359. Min Act: -0.1700
Data Index: 3989292 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8797. Min Range: -6.8797
Max Act: 6.5672. Min Act: -0.1700
Data Index: 5086961 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8797. Min Range: -6.8797
Max Act: 6.5672. Min Act: -0.1700
Data Index: 6890253 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8797. Min Range: -6.8797
Max Act: 6.4734. Min Act: -0.1700
Data Index: 2141800 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8797. Min Range: -6.8797
Max Act: 6.5047. Min Act: -0.1700
Data Index: 1734479 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8797. Min Range: -6.8797
Max Act: 6.4734. Min Act: -0.1700
Data Index: 3939918 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8797. Min Range: -6.8797
Max Act: 6.4734. Min Act: -0.1700
Data Index: 5484216 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19