Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3768 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6995. Min Range: -7.6995
Max Act: 7.6995. Min Act: -0.1700
Data Index: 6292543 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6995. Min Range: -7.6995
Max Act: 7.5432. Min Act: -0.1700
Data Index: 2464053 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6995. Min Range: -7.6995
Max Act: 7.3870. Min Act: -0.1700
Data Index: 8734021 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6995. Min Range: -7.6995
Max Act: 7.3557. Min Act: -0.1700
Data Index: 5438945 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6995. Min Range: -7.6995
Max Act: 7.3245. Min Act: -0.1700
Data Index: 6343874 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6995. Min Range: -7.6995
Max Act: 7.3245. Min Act: -0.1700
Data Index: 5788923 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6995. Min Range: -7.6995
Max Act: 7.3245. Min Act: -0.1700
Data Index: 5764383 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6995. Min Range: -7.6995
Max Act: 7.2932. Min Act: -0.1700
Data Index: 5036404 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6995. Min Range: -7.6995
Max Act: 7.2932. Min Act: -0.1700
Data Index: 4007861 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6995. Min Range: -7.6995
Max Act: 7.2932. Min Act: -0.1700
Data Index: 713496 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6995. Min Range: -7.6995
Max Act: 7.2932. Min Act: -0.1700
Data Index: 1456751 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6995. Min Range: -7.6995
Max Act: 7.2932. Min Act: -0.1700
Data Index: 2314448 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6995. Min Range: -7.6995
Max Act: 7.2620. Min Act: -0.1700
Data Index: 218530 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6995. Min Range: -7.6995
Max Act: 7.2932. Min Act: -0.1700
Data Index: 3377201 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6995. Min Range: -7.6995
Max Act: 7.2307. Min Act: -0.1700
Data Index: 538046 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6995. Min Range: -7.6995
Max Act: 7.1995. Min Act: -0.1700
Data Index: 8581862 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6995. Min Range: -7.6995
Max Act: 7.1682. Min Act: -0.1700
Data Index: 7225310 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6995. Min Range: -7.6995
Max Act: 7.1370. Min Act: -0.1700
Data Index: 7486363 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6995. Min Range: -7.6995
Max Act: 7.1370. Min Act: -0.1700
Data Index: 969871 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6995. Min Range: -7.6995
Max Act: 7.1370. Min Act: -0.1700
Data Index: 8795478 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19