Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6354 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.9202. Min Act: -0.1700
Data Index: 1744919 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.8577. Min Act: -0.1700
Data Index: 3919510 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.7327. Min Act: -0.1700
Data Index: 1017126 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.6389. Min Act: -0.1700
Data Index: 7166160 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.5452. Min Act: -0.1700
Data Index: 6534099 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.4827. Min Act: -0.1700
Data Index: 5715345 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.5139. Min Act: -0.1700
Data Index: 3303101 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.5139. Min Act: -0.1700
Data Index: 5958018 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.4827. Min Act: -0.1700
Data Index: 7450906 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.4827. Min Act: -0.1700
Data Index: 2515960 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.4827. Min Act: -0.1700
Data Index: 4511056 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.4514. Min Act: -0.1700
Data Index: 4473248 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.4514. Min Act: -0.1700
Data Index: 8271184 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.4202. Min Act: -0.1700
Data Index: 7070241 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.4514. Min Act: -0.1700
Data Index: 3479830 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.4514. Min Act: -0.1700
Data Index: 7068687 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.4514. Min Act: -0.1700
Data Index: 5540547 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.4202. Min Act: -0.1700
Data Index: 2002306 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.4202. Min Act: -0.1700
Data Index: 3321313 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.4202. Min Act: -0.1700
Data Index: 2039566 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19