Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5853 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5945. Min Range: -6.5945
Max Act: 6.5945. Min Act: -0.1700
Data Index: 7965057 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5945. Min Range: -6.5945
Max Act: 6.5945. Min Act: -0.1700
Data Index: 782356 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5945. Min Range: -6.5945
Max Act: 6.5632. Min Act: -0.1700
Data Index: 3392090 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5945. Min Range: -6.5945
Max Act: 6.5320. Min Act: -0.1700
Data Index: 5841108 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5945. Min Range: -6.5945
Max Act: 6.5007. Min Act: -0.1700
Data Index: 6463458 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5945. Min Range: -6.5945
Max Act: 6.4070. Min Act: -0.1700
Data Index: 1015018 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5945. Min Range: -6.5945
Max Act: 6.4070. Min Act: -0.1700
Data Index: 3066273 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5945. Min Range: -6.5945
Max Act: 6.3757. Min Act: -0.1700
Data Index: 7259889 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5945. Min Range: -6.5945
Max Act: 6.3132. Min Act: -0.1700
Data Index: 693841 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5945. Min Range: -6.5945
Max Act: 6.3445. Min Act: -0.1700
Data Index: 4147677 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5945. Min Range: -6.5945
Max Act: 6.3757. Min Act: -0.1700
Data Index: 4028163 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5945. Min Range: -6.5945
Max Act: 6.3445. Min Act: -0.1700
Data Index: 7527172 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5945. Min Range: -6.5945
Max Act: 6.2820. Min Act: -0.1700
Data Index: 3865065 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5945. Min Range: -6.5945
Max Act: 6.2820. Min Act: -0.1700
Data Index: 6626818 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5945. Min Range: -6.5945
Max Act: 6.3132. Min Act: -0.1700
Data Index: 4223323 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5945. Min Range: -6.5945
Max Act: 6.2820. Min Act: -0.1700
Data Index: 6681425 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5945. Min Range: -6.5945
Max Act: 6.2507. Min Act: -0.1700
Data Index: 6753524 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5945. Min Range: -6.5945
Max Act: 6.2195. Min Act: -0.1700
Data Index: 2184532 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5945. Min Range: -6.5945
Max Act: 6.1882. Min Act: -0.1700
Data Index: 3341030 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5945. Min Range: -6.5945
Max Act: 6.2195. Min Act: -0.1700
Data Index: 4552473 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19