Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.4308. Min Act: -0.1700
Data Index: 7231372 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.2745. Min Act: -0.1700
Data Index: 2772381 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.2120. Min Act: -0.1700
Data Index: 7692547 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.2120. Min Act: -0.1700
Data Index: 2744536 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.1808. Min Act: -0.1700
Data Index: 2632809 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.1183. Min Act: -0.1700
Data Index: 4937660 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.1495. Min Act: -0.1700
Data Index: 2272375 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.1183. Min Act: -0.1700
Data Index: 5902483 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.1183. Min Act: -0.1700
Data Index: 5447924 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.0870. Min Act: -0.1700
Data Index: 2190148 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.0558. Min Act: -0.1700
Data Index: 720397 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.0558. Min Act: -0.1700
Data Index: 4523672 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.0558. Min Act: -0.1700
Data Index: 5062029 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.0558. Min Act: -0.1700
Data Index: 7533212 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.0245. Min Act: -0.1700
Data Index: 6432777 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.0245. Min Act: -0.1700
Data Index: 535135 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4308. Min Range: -5.4308
Max Act: 4.9932. Min Act: -0.1700
Data Index: 1611118 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.0245. Min Act: -0.1700
Data Index: 2599348 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4308. Min Range: -5.4308
Max Act: 4.9932. Min Act: -0.1700
Data Index: 3862045 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4308. Min Range: -5.4308
Max Act: 4.9932. Min Act: -0.1700
Data Index: 3583989 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19