Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2919 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8658. Min Range: -4.8658
Max Act: 4.8658. Min Act: -0.1700
Data Index: 8430773 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8658. Min Range: -4.8658
Max Act: 4.8033. Min Act: -0.1700
Data Index: 8239058 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8658. Min Range: -4.8658
Max Act: 4.6470. Min Act: -0.1700
Data Index: 126824 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8658. Min Range: -4.8658
Max Act: 4.6470. Min Act: -0.1700
Data Index: 7844787 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8658. Min Range: -4.8658
Max Act: 4.5533. Min Act: -0.1700
Data Index: 2247028 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8658. Min Range: -4.8658
Max Act: 4.5845. Min Act: -0.1700
Data Index: 3623933 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8658. Min Range: -4.8658
Max Act: 4.6158. Min Act: -0.1700
Data Index: 4320005 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8658. Min Range: -4.8658
Max Act: 4.5533. Min Act: -0.1700
Data Index: 6852663 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8658. Min Range: -4.8658
Max Act: 4.5220. Min Act: -0.1700
Data Index: 2416604 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8658. Min Range: -4.8658
Max Act: 4.5533. Min Act: -0.1700
Data Index: 3850168 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8658. Min Range: -4.8658
Max Act: 4.5220. Min Act: -0.1700
Data Index: 5288611 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8658. Min Range: -4.8658
Max Act: 4.5220. Min Act: -0.1700
Data Index: 1538769 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8658. Min Range: -4.8658
Max Act: 4.5220. Min Act: -0.1700
Data Index: 7157913 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8658. Min Range: -4.8658
Max Act: 4.4908. Min Act: -0.1700
Data Index: 6632174 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8658. Min Range: -4.8658
Max Act: 4.4908. Min Act: -0.1700
Data Index: 8810563 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8658. Min Range: -4.8658
Max Act: 4.4595. Min Act: -0.1700
Data Index: 87178 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8658. Min Range: -4.8658
Max Act: 4.4283. Min Act: -0.1700
Data Index: 3689342 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8658. Min Range: -4.8658
Max Act: 4.4595. Min Act: -0.1700
Data Index: 1768390 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8658. Min Range: -4.8658
Max Act: 4.4595. Min Act: -0.1700
Data Index: 2459409 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8658. Min Range: -4.8658
Max Act: 4.4595. Min Act: -0.1700
Data Index: 1638399 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19