Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2003 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8047. Min Range: -4.8047
Max Act: 4.8047. Min Act: -0.1700
Data Index: 3993495 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8047. Min Range: -4.8047
Max Act: 4.8047. Min Act: -0.1700
Data Index: 1865494 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8047. Min Range: -4.8047
Max Act: 4.7109. Min Act: -0.1700
Data Index: 3152576 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8047. Min Range: -4.8047
Max Act: 4.7422. Min Act: -0.1700
Data Index: 715121 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8047. Min Range: -4.8047
Max Act: 4.6484. Min Act: -0.1700
Data Index: 2642573 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8047. Min Range: -4.8047
Max Act: 4.6484. Min Act: -0.1700
Data Index: 3152412 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8047. Min Range: -4.8047
Max Act: 4.6797. Min Act: -0.1700
Data Index: 817804 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8047. Min Range: -4.8047
Max Act: 4.6484. Min Act: -0.1700
Data Index: 6791075 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8047. Min Range: -4.8047
Max Act: 4.6172. Min Act: -0.1700
Data Index: 8206273 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8047. Min Range: -4.8047
Max Act: 4.5859. Min Act: -0.1700
Data Index: 1123698 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8047. Min Range: -4.8047
Max Act: 4.5859. Min Act: -0.1700
Data Index: 7909503 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8047. Min Range: -4.8047
Max Act: 4.5547. Min Act: -0.1700
Data Index: 7704092 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8047. Min Range: -4.8047
Max Act: 4.5547. Min Act: -0.1700
Data Index: 4750080 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8047. Min Range: -4.8047
Max Act: 4.5234. Min Act: -0.1700
Data Index: 463460 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8047. Min Range: -4.8047
Max Act: 4.5547. Min Act: -0.1700
Data Index: 299260 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8047. Min Range: -4.8047
Max Act: 4.5547. Min Act: -0.1700
Data Index: 7885800 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8047. Min Range: -4.8047
Max Act: 4.5234. Min Act: -0.1700
Data Index: 7637077 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8047. Min Range: -4.8047
Max Act: 4.5234. Min Act: -0.1700
Data Index: 4688808 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8047. Min Range: -4.8047
Max Act: 4.5234. Min Act: -0.1700
Data Index: 4369966 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8047. Min Range: -4.8047
Max Act: 4.5234. Min Act: -0.1700
Data Index: 4548675 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19