Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4072 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8326. Min Range: -2.8326
Max Act: 2.8326. Min Act: -0.1700
Data Index: 594073 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8326. Min Range: -2.8326
Max Act: 2.8326. Min Act: -0.1700
Data Index: 2265543 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8326. Min Range: -2.8326
Max Act: 2.8008. Min Act: -0.1700
Data Index: 8082202 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8326. Min Range: -2.8326
Max Act: 2.7848. Min Act: -0.1700
Data Index: 7405456 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8326. Min Range: -2.8326
Max Act: 2.7848. Min Act: -0.1700
Data Index: 3551145 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8326. Min Range: -2.8326
Max Act: 2.7689. Min Act: -0.1700
Data Index: 6180522 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8326. Min Range: -2.8326
Max Act: 2.7848. Min Act: -0.1700
Data Index: 4656889 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8326. Min Range: -2.8326
Max Act: 2.7848. Min Act: -0.1700
Data Index: 2621189 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8326. Min Range: -2.8326
Max Act: 2.7689. Min Act: -0.1700
Data Index: 8391470 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8326. Min Range: -2.8326
Max Act: 2.7689. Min Act: -0.1700
Data Index: 495824 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8326. Min Range: -2.8326
Max Act: 2.7689. Min Act: -0.1700
Data Index: 3347123 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8326. Min Range: -2.8326
Max Act: 2.7530. Min Act: -0.1700
Data Index: 6745815 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8326. Min Range: -2.8326
Max Act: 2.7530. Min Act: -0.1700
Data Index: 7072461 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8326. Min Range: -2.8326
Max Act: 2.7370. Min Act: -0.1700
Data Index: 4073244 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8326. Min Range: -2.8326
Max Act: 2.7210. Min Act: -0.1700
Data Index: 7253493 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8326. Min Range: -2.8326
Max Act: 2.7210. Min Act: -0.1700
Data Index: 5543261 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8326. Min Range: -2.8326
Max Act: 2.7370. Min Act: -0.1700
Data Index: 8268655 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8326. Min Range: -2.8326
Max Act: 2.7210. Min Act: -0.1700
Data Index: 7349568 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8326. Min Range: -2.8326
Max Act: 2.7050. Min Act: -0.1700
Data Index: 6198112 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8326. Min Range: -2.8326
Max Act: 2.7050. Min Act: -0.1700
Data Index: 6571157 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19