Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4321 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3231. Min Range: -7.3231
Max Act: 7.3231. Min Act: -0.1700
Data Index: 2337832 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3231. Min Range: -7.3231
Max Act: 7.2294. Min Act: -0.1700
Data Index: 8187472 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3231. Min Range: -7.3231
Max Act: 7.1669. Min Act: -0.1700
Data Index: 3458915 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3231. Min Range: -7.3231
Max Act: 7.1356. Min Act: -0.1700
Data Index: 6619274 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3231. Min Range: -7.3231
Max Act: 7.0731. Min Act: -0.1700
Data Index: 4627307 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3231. Min Range: -7.3231
Max Act: 6.9169. Min Act: -0.1700
Data Index: 7115618 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3231. Min Range: -7.3231
Max Act: 6.9169. Min Act: -0.1700
Data Index: 8513065 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3231. Min Range: -7.3231
Max Act: 6.9481. Min Act: -0.1700
Data Index: 4093622 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3231. Min Range: -7.3231
Max Act: 6.9481. Min Act: -0.1700
Data Index: 6782328 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3231. Min Range: -7.3231
Max Act: 6.9481. Min Act: -0.1700
Data Index: 4893544 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3231. Min Range: -7.3231
Max Act: 6.8856. Min Act: -0.1700
Data Index: 5585925 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3231. Min Range: -7.3231
Max Act: 6.8856. Min Act: -0.1700
Data Index: 1908341 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3231. Min Range: -7.3231
Max Act: 6.8544. Min Act: -0.1700
Data Index: 3008265 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3231. Min Range: -7.3231
Max Act: 6.8544. Min Act: -0.1700
Data Index: 2802879 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3231. Min Range: -7.3231
Max Act: 6.8544. Min Act: -0.1700
Data Index: 5430410 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3231. Min Range: -7.3231
Max Act: 6.8231. Min Act: -0.1700
Data Index: 8772379 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3231. Min Range: -7.3231
Max Act: 6.7919. Min Act: -0.1700
Data Index: 3763918 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3231. Min Range: -7.3231
Max Act: 6.7919. Min Act: -0.1700
Data Index: 3027485 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3231. Min Range: -7.3231
Max Act: 6.7919. Min Act: -0.1700
Data Index: 4749166 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3231. Min Range: -7.3231
Max Act: 6.7919. Min Act: -0.1700
Data Index: 2050029 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19