Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1314 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1341. Min Range: -6.1341
Max Act: 6.1341. Min Act: -0.1700
Data Index: 6737772 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1341. Min Range: -6.1341
Max Act: 5.7278. Min Act: -0.1700
Data Index: 2832554 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1341. Min Range: -6.1341
Max Act: 5.6653. Min Act: -0.1700
Data Index: 4870346 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1341. Min Range: -6.1341
Max Act: 5.6653. Min Act: -0.1700
Data Index: 3070917 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1341. Min Range: -6.1341
Max Act: 5.6028. Min Act: -0.1700
Data Index: 6013253 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1341. Min Range: -6.1341
Max Act: 5.6341. Min Act: -0.1700
Data Index: 2035955 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1341. Min Range: -6.1341
Max Act: 5.6028. Min Act: -0.1700
Data Index: 8129320 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1341. Min Range: -6.1341
Max Act: 5.6028. Min Act: -0.1700
Data Index: 2832551 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1341. Min Range: -6.1341
Max Act: 5.6341. Min Act: -0.1700
Data Index: 1970367 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1341. Min Range: -6.1341
Max Act: 5.6028. Min Act: -0.1700
Data Index: 8596136 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1341. Min Range: -6.1341
Max Act: 5.5716. Min Act: -0.1700
Data Index: 7333012 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1341. Min Range: -6.1341
Max Act: 5.5716. Min Act: -0.1700
Data Index: 2072072 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1341. Min Range: -6.1341
Max Act: 5.6028. Min Act: -0.1700
Data Index: 7592505 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1341. Min Range: -6.1341
Max Act: 5.5403. Min Act: -0.1700
Data Index: 2928607 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1341. Min Range: -6.1341
Max Act: 5.5716. Min Act: -0.1700
Data Index: 2985137 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1341. Min Range: -6.1341
Max Act: 5.5091. Min Act: -0.1700
Data Index: 4004951 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1341. Min Range: -6.1341
Max Act: 5.5403. Min Act: -0.1700
Data Index: 1232558 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1341. Min Range: -6.1341
Max Act: 5.5091. Min Act: -0.1700
Data Index: 1273132 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1341. Min Range: -6.1341
Max Act: 5.4778. Min Act: -0.1700
Data Index: 3094959 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1341. Min Range: -6.1341
Max Act: 5.4778. Min Act: -0.1700
Data Index: 1918129 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19