Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2675 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3941. Min Range: -8.3941
Max Act: 8.3941. Min Act: -0.1700
Data Index: 2649818 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3941. Min Range: -8.3941
Max Act: 8.3316. Min Act: -0.1700
Data Index: 413319 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3941. Min Range: -8.3941
Max Act: 8.3316. Min Act: -0.1700
Data Index: 372469 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3941. Min Range: -8.3941
Max Act: 8.2691. Min Act: -0.1700
Data Index: 8014234 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3941. Min Range: -8.3941
Max Act: 8.2066. Min Act: -0.1700
Data Index: 7642108 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3941. Min Range: -8.3941
Max Act: 8.2691. Min Act: -0.1700
Data Index: 2125188 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3941. Min Range: -8.3941
Max Act: 8.2066. Min Act: -0.1700
Data Index: 2290684 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3941. Min Range: -8.3941
Max Act: 8.2066. Min Act: -0.1700
Data Index: 1387850 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3941. Min Range: -8.3941
Max Act: 8.2066. Min Act: -0.1699
Data Index: 8577526 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3941. Min Range: -8.3941
Max Act: 8.1441. Min Act: -0.1700
Data Index: 2116533 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3941. Min Range: -8.3941
Max Act: 8.1441. Min Act: -0.1700
Data Index: 8805591 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3941. Min Range: -8.3941
Max Act: 8.1441. Min Act: -0.1700
Data Index: 1032173 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3941. Min Range: -8.3941
Max Act: 8.1441. Min Act: -0.1700
Data Index: 7615380 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3941. Min Range: -8.3941
Max Act: 8.1441. Min Act: -0.1700
Data Index: 8436415 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3941. Min Range: -8.3941
Max Act: 8.1441. Min Act: -0.1700
Data Index: 1744656 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3941. Min Range: -8.3941
Max Act: 8.1441. Min Act: -0.1700
Data Index: 2414905 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3941. Min Range: -8.3941
Max Act: 8.0816. Min Act: -0.1700
Data Index: 2430958 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3941. Min Range: -8.3941
Max Act: 8.0816. Min Act: -0.1700
Data Index: 2300678 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3941. Min Range: -8.3941
Max Act: 8.0816. Min Act: -0.1700
Data Index: 1605641 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3941. Min Range: -8.3941
Max Act: 8.0191. Min Act: -0.1700
Data Index: 2106498 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19