Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3888 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.1172. Min Range: -13.1172
Max Act: 13.1172. Min Act: -0.1700
Data Index: 7958359 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.1172. Min Range: -13.1172
Max Act: 12.9922. Min Act: -0.1700
Data Index: 7859417 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.1172. Min Range: -13.1172
Max Act: 13.0547. Min Act: -0.1700
Data Index: 3574780 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.1172. Min Range: -13.1172
Max Act: 12.9297. Min Act: -0.1700
Data Index: 2314657 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.1172. Min Range: -13.1172
Max Act: 12.8672. Min Act: -0.1700
Data Index: 5453526 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.1172. Min Range: -13.1172
Max Act: 12.8672. Min Act: -0.1700
Data Index: 5115696 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.1172. Min Range: -13.1172
Max Act: 12.8672. Min Act: -0.1700
Data Index: 7578569 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.1172. Min Range: -13.1172
Max Act: 12.8047. Min Act: -0.1700
Data Index: 930712 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.1172. Min Range: -13.1172
Max Act: 12.8047. Min Act: -0.1700
Data Index: 7386663 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.1172. Min Range: -13.1172
Max Act: 12.8047. Min Act: -0.1700
Data Index: 3754385 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.1172. Min Range: -13.1172
Max Act: 12.8047. Min Act: -0.1700
Data Index: 8384546 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.1172. Min Range: -13.1172
Max Act: 12.6797. Min Act: -0.1700
Data Index: 6701214 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.1172. Min Range: -13.1172
Max Act: 12.6172. Min Act: -0.1700
Data Index: 5965644 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.1172. Min Range: -13.1172
Max Act: 12.6172. Min Act: -0.1700
Data Index: 6792332 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.1172. Min Range: -13.1172
Max Act: 12.6172. Min Act: -0.1700
Data Index: 7822758 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.1172. Min Range: -13.1172
Max Act: 12.6172. Min Act: -0.1700
Data Index: 5185580 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.1172. Min Range: -13.1172
Max Act: 12.5547. Min Act: -0.1700
Data Index: 4567844 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.1172. Min Range: -13.1172
Max Act: 12.5547. Min Act: -0.1700
Data Index: 7815355 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.1172. Min Range: -13.1172
Max Act: 12.5547. Min Act: -0.1700
Data Index: 2544930 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.1172. Min Range: -13.1172
Max Act: 12.4922. Min Act: -0.1700
Data Index: 7782680 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19