Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4058 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.8956. Min Range: -10.8956
Max Act: 10.8956. Min Act: -0.1700
Data Index: 7311720 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8956. Min Range: -10.8956
Max Act: 10.7081. Min Act: -0.1700
Data Index: 12170 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8956. Min Range: -10.8956
Max Act: 10.7081. Min Act: -0.1700
Data Index: 8562390 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8956. Min Range: -10.8956
Max Act: 10.5831. Min Act: -0.1700
Data Index: 1228959 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8956. Min Range: -10.8956
Max Act: 10.3956. Min Act: -0.1700
Data Index: 6357679 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8956. Min Range: -10.8956
Max Act: 10.3331. Min Act: -0.1700
Data Index: 7681252 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8956. Min Range: -10.8956
Max Act: 10.2706. Min Act: -0.1700
Data Index: 6891906 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8956. Min Range: -10.8956
Max Act: 10.2081. Min Act: -0.1700
Data Index: 848879 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8956. Min Range: -10.8956
Max Act: 10.2081. Min Act: -0.1700
Data Index: 8295491 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8956. Min Range: -10.8956
Max Act: 10.0831. Min Act: -0.1700
Data Index: 4319392 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8956. Min Range: -10.8956
Max Act: 10.0206. Min Act: -0.1700
Data Index: 5420549 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8956. Min Range: -10.8956
Max Act: 10.0831. Min Act: -0.1700
Data Index: 5557222 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8956. Min Range: -10.8956
Max Act: 10.0206. Min Act: -0.1698
Data Index: 6975055 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8956. Min Range: -10.8956
Max Act: 10.0206. Min Act: -0.1700
Data Index: 5989434 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8956. Min Range: -10.8956
Max Act: 10.0206. Min Act: -0.1700
Data Index: 5644418 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8956. Min Range: -10.8956
Max Act: 9.9581. Min Act: -0.1700
Data Index: 6127160 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8956. Min Range: -10.8956
Max Act: 9.8956. Min Act: -0.1700
Data Index: 2406166 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8956. Min Range: -10.8956
Max Act: 9.9581. Min Act: -0.1700
Data Index: 7316814 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8956. Min Range: -10.8956
Max Act: 9.8331. Min Act: -0.1700
Data Index: 6305259 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8956. Min Range: -10.8956
Max Act: 9.8331. Min Act: -0.1700
Data Index: 2936802 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19