Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2688 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7342. Min Range: -4.7342
Max Act: 4.7342. Min Act: -0.1700
Data Index: 185243 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7342. Min Range: -4.7342
Max Act: 4.7342. Min Act: -0.1700
Data Index: 8435700 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7342. Min Range: -4.7342
Max Act: 4.6717. Min Act: -0.1700
Data Index: 5318717 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7342. Min Range: -4.7342
Max Act: 4.6405. Min Act: -0.1700
Data Index: 2586343 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7342. Min Range: -4.7342
Max Act: 4.6092. Min Act: -0.1700
Data Index: 1682582 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7342. Min Range: -4.7342
Max Act: 4.6092. Min Act: -0.1700
Data Index: 1663856 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7342. Min Range: -4.7342
Max Act: 4.5780. Min Act: -0.1700
Data Index: 3366851 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7342. Min Range: -4.7342
Max Act: 4.5467. Min Act: -0.1700
Data Index: 4930710 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7342. Min Range: -4.7342
Max Act: 4.5467. Min Act: -0.1700
Data Index: 4149411 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7342. Min Range: -4.7342
Max Act: 4.5155. Min Act: -0.1700
Data Index: 7199999 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7342. Min Range: -4.7342
Max Act: 4.5155. Min Act: -0.1700
Data Index: 489984 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7342. Min Range: -4.7342
Max Act: 4.5155. Min Act: -0.1700
Data Index: 4149410 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7342. Min Range: -4.7342
Max Act: 4.5155. Min Act: -0.1700
Data Index: 6570337 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7342. Min Range: -4.7342
Max Act: 4.4842. Min Act: -0.1700
Data Index: 8273052 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7342. Min Range: -4.7342
Max Act: 4.5155. Min Act: -0.1700
Data Index: 2463972 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7342. Min Range: -4.7342
Max Act: 4.4530. Min Act: -0.1700
Data Index: 7583910 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7342. Min Range: -4.7342
Max Act: 4.4530. Min Act: -0.1700
Data Index: 719480 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7342. Min Range: -4.7342
Max Act: 4.4530. Min Act: -0.1700
Data Index: 4466202 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7342. Min Range: -4.7342
Max Act: 4.4530. Min Act: -0.1700
Data Index: 4466203 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7342. Min Range: -4.7342
Max Act: 4.4530. Min Act: -0.1700
Data Index: 4106924 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19