Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3161 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2362. Min Range: -5.2362
Max Act: 5.2362. Min Act: -0.1700
Data Index: 1774869 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2362. Min Range: -5.2362
Max Act: 5.0800. Min Act: -0.1700
Data Index: 1502553 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2362. Min Range: -5.2362
Max Act: 5.1112. Min Act: -0.1700
Data Index: 7955339 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2362. Min Range: -5.2362
Max Act: 5.0487. Min Act: -0.1700
Data Index: 1700299 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2362. Min Range: -5.2362
Max Act: 5.0487. Min Act: -0.1700
Data Index: 7271485 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2362. Min Range: -5.2362
Max Act: 4.9862. Min Act: -0.1700
Data Index: 152899 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2362. Min Range: -5.2362
Max Act: 4.9862. Min Act: -0.1700
Data Index: 5800764 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2362. Min Range: -5.2362
Max Act: 4.9237. Min Act: -0.1700
Data Index: 882187 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2362. Min Range: -5.2362
Max Act: 4.9550. Min Act: -0.1700
Data Index: 4166146 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2362. Min Range: -5.2362
Max Act: 4.9237. Min Act: -0.1700
Data Index: 5333111 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2362. Min Range: -5.2362
Max Act: 4.9550. Min Act: -0.1700
Data Index: 5243743 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2362. Min Range: -5.2362
Max Act: 4.8925. Min Act: -0.1700
Data Index: 666295 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2362. Min Range: -5.2362
Max Act: 4.9237. Min Act: -0.1700
Data Index: 1336942 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2362. Min Range: -5.2362
Max Act: 4.9237. Min Act: -0.1700
Data Index: 6727891 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2362. Min Range: -5.2362
Max Act: 4.9550. Min Act: -0.1700
Data Index: 1524438 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2362. Min Range: -5.2362
Max Act: 4.8925. Min Act: -0.1700
Data Index: 8124687 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2362. Min Range: -5.2362
Max Act: 4.8925. Min Act: -0.1700
Data Index: 5643964 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2362. Min Range: -5.2362
Max Act: 4.8612. Min Act: -0.1700
Data Index: 4708059 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2362. Min Range: -5.2362
Max Act: 4.8925. Min Act: -0.1700
Data Index: 8136389 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2362. Min Range: -5.2362
Max Act: 4.8925. Min Act: -0.1700
Data Index: 6582247 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19