Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3366 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7250. Min Range: -1.7250
Max Act: 1.7250. Min Act: -0.1700
Data Index: 5970802 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7250. Min Range: -1.7250
Max Act: 1.6817. Min Act: -0.1700
Data Index: 6867628 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7250. Min Range: -1.7250
Max Act: 1.6730. Min Act: -0.1700
Data Index: 1298148 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7250. Min Range: -1.7250
Max Act: 1.6730. Min Act: -0.1700
Data Index: 6678101 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7250. Min Range: -1.7250
Max Act: 1.6469. Min Act: -0.1700
Data Index: 3642470 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7250. Min Range: -1.7250
Max Act: 1.6556. Min Act: -0.1700
Data Index: 1025858 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7250. Min Range: -1.7250
Max Act: 1.6469. Min Act: -0.1700
Data Index: 1361915 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7250. Min Range: -1.7250
Max Act: 1.6469. Min Act: -0.1700
Data Index: 698787 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7250. Min Range: -1.7250
Max Act: 1.6382. Min Act: -0.1700
Data Index: 5529678 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7250. Min Range: -1.7250
Max Act: 1.6295. Min Act: -0.1700
Data Index: 8320912 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7250. Min Range: -1.7250
Max Act: 1.6295. Min Act: -0.1700
Data Index: 4480793 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7250. Min Range: -1.7250
Max Act: 1.6207. Min Act: -0.1700
Data Index: 7391400 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7250. Min Range: -1.7250
Max Act: 1.6207. Min Act: -0.1700
Data Index: 804666 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7250. Min Range: -1.7250
Max Act: 1.6120. Min Act: -0.1700
Data Index: 5920910 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7250. Min Range: -1.7250
Max Act: 1.6295. Min Act: -0.1700
Data Index: 3158899 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7250. Min Range: -1.7250
Max Act: 1.6207. Min Act: -0.1700
Data Index: 2941769 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7250. Min Range: -1.7250
Max Act: 1.6207. Min Act: -0.1700
Data Index: 7653599 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7250. Min Range: -1.7250
Max Act: 1.6295. Min Act: -0.1700
Data Index: 1542917 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7250. Min Range: -1.7250
Max Act: 1.6207. Min Act: -0.1700
Data Index: 1008815 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7250. Min Range: -1.7250
Max Act: 1.6207. Min Act: -0.1700
Data Index: 6417852 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19