Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2962 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2713. Min Range: -7.2713
Max Act: 7.2713. Min Act: -0.1700
Data Index: 3310221 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2713. Min Range: -7.2713
Max Act: 7.2401. Min Act: -0.1700
Data Index: 3818324 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2713. Min Range: -7.2713
Max Act: 7.1776. Min Act: -0.1700
Data Index: 2455643 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2713. Min Range: -7.2713
Max Act: 7.1151. Min Act: -0.1700
Data Index: 986557 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2713. Min Range: -7.2713
Max Act: 7.0838. Min Act: -0.1700
Data Index: 3226846 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2713. Min Range: -7.2713
Max Act: 7.0838. Min Act: -0.1700
Data Index: 8797595 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2713. Min Range: -7.2713
Max Act: 7.0213. Min Act: -0.1700
Data Index: 4251061 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2713. Min Range: -7.2713
Max Act: 7.0213. Min Act: -0.1700
Data Index: 5335156 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2713. Min Range: -7.2713
Max Act: 7.0213. Min Act: -0.1700
Data Index: 3697245 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2713. Min Range: -7.2713
Max Act: 6.9901. Min Act: -0.1700
Data Index: 5531745 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2713. Min Range: -7.2713
Max Act: 6.9588. Min Act: -0.1700
Data Index: 8395945 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2713. Min Range: -7.2713
Max Act: 6.8963. Min Act: -0.1700
Data Index: 8797586 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2713. Min Range: -7.2713
Max Act: 6.8651. Min Act: -0.1700
Data Index: 6503895 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2713. Min Range: -7.2713
Max Act: 6.8651. Min Act: -0.1700
Data Index: 8797599 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2713. Min Range: -7.2713
Max Act: 6.8338. Min Act: -0.1700
Data Index: 1016462 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2713. Min Range: -7.2713
Max Act: 6.8026. Min Act: -0.1700
Data Index: 5418418 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2713. Min Range: -7.2713
Max Act: 6.7088. Min Act: -0.1700
Data Index: 1369654 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2713. Min Range: -7.2713
Max Act: 6.7401. Min Act: -0.1700
Data Index: 535776 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2713. Min Range: -7.2713
Max Act: 6.7401. Min Act: -0.1700
Data Index: 3304470 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2713. Min Range: -7.2713
Max Act: 6.7088. Min Act: -0.1700
Data Index: 7261671 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19