Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4071 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9683. Min Range: -5.9683
Max Act: 5.9683. Min Act: -0.1700
Data Index: 552537 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9683. Min Range: -5.9683
Max Act: 5.9058. Min Act: -0.1700
Data Index: 2496042 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9683. Min Range: -5.9683
Max Act: 5.8746. Min Act: -0.1700
Data Index: 447052 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9683. Min Range: -5.9683
Max Act: 5.8121. Min Act: -0.1700
Data Index: 5596762 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9683. Min Range: -5.9683
Max Act: 5.7808. Min Act: -0.1700
Data Index: 5613473 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9683. Min Range: -5.9683
Max Act: 5.7496. Min Act: -0.1700
Data Index: 2006574 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9683. Min Range: -5.9683
Max Act: 5.6558. Min Act: -0.1700
Data Index: 4500131 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9683. Min Range: -5.9683
Max Act: 5.6558. Min Act: -0.1700
Data Index: 6024603 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9683. Min Range: -5.9683
Max Act: 5.6558. Min Act: -0.1700
Data Index: 951353 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9683. Min Range: -5.9683
Max Act: 5.5933. Min Act: -0.1700
Data Index: 490966 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9683. Min Range: -5.9683
Max Act: 5.5933. Min Act: -0.1700
Data Index: 7435236 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9683. Min Range: -5.9683
Max Act: 5.5308. Min Act: -0.1700
Data Index: 4154229 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9683. Min Range: -5.9683
Max Act: 5.5621. Min Act: -0.1700
Data Index: 6361256 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9683. Min Range: -5.9683
Max Act: 5.5621. Min Act: -0.1700
Data Index: 5613471 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9683. Min Range: -5.9683
Max Act: 5.4683. Min Act: -0.1700
Data Index: 5263688 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9683. Min Range: -5.9683
Max Act: 5.4996. Min Act: -0.1700
Data Index: 627358 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9683. Min Range: -5.9683
Max Act: 5.4683. Min Act: -0.1700
Data Index: 5239967 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9683. Min Range: -5.9683
Max Act: 5.4683. Min Act: -0.1700
Data Index: 4713407 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9683. Min Range: -5.9683
Max Act: 5.4371. Min Act: -0.1700
Data Index: 6938132 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9683. Min Range: -5.9683
Max Act: 5.4058. Min Act: -0.1700
Data Index: 5901235 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19