Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3192 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9901. Min Range: -7.9901
Max Act: 7.9901. Min Act: -0.1700
Data Index: 5416566 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9901. Min Range: -7.9901
Max Act: 7.9276. Min Act: -0.1700
Data Index: 8677635 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9901. Min Range: -7.9901
Max Act: 7.9276. Min Act: -0.1700
Data Index: 7890428 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9901. Min Range: -7.9901
Max Act: 7.8963. Min Act: -0.1700
Data Index: 7068271 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9901. Min Range: -7.9901
Max Act: 7.6151. Min Act: -0.1700
Data Index: 1883774 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9901. Min Range: -7.9901
Max Act: 7.3651. Min Act: -0.1700
Data Index: 4726924 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9901. Min Range: -7.9901
Max Act: 7.3026. Min Act: -0.1700
Data Index: 8364085 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9901. Min Range: -7.9901
Max Act: 7.2713. Min Act: -0.1700
Data Index: 2315659 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9901. Min Range: -7.9901
Max Act: 7.3026. Min Act: -0.1700
Data Index: 1710473 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9901. Min Range: -7.9901
Max Act: 7.2401. Min Act: -0.1700
Data Index: 4850631 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9901. Min Range: -7.9901
Max Act: 7.2401. Min Act: -0.1700
Data Index: 375617 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9901. Min Range: -7.9901
Max Act: 7.2088. Min Act: -0.1700
Data Index: 5331687 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9901. Min Range: -7.9901
Max Act: 7.2401. Min Act: -0.1700
Data Index: 1385537 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9901. Min Range: -7.9901
Max Act: 7.2088. Min Act: -0.1700
Data Index: 1893786 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9901. Min Range: -7.9901
Max Act: 7.2088. Min Act: -0.1700
Data Index: 6432562 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9901. Min Range: -7.9901
Max Act: 7.2088. Min Act: -0.1700
Data Index: 6521871 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9901. Min Range: -7.9901
Max Act: 7.2088. Min Act: -0.1700
Data Index: 4773813 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9901. Min Range: -7.9901
Max Act: 7.1776. Min Act: -0.1700
Data Index: 7497118 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9901. Min Range: -7.9901
Max Act: 7.1776. Min Act: -0.1700
Data Index: 781227 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9901. Min Range: -7.9901
Max Act: 7.1463. Min Act: -0.1700
Data Index: 2800339 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19