Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2904 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.5458. Min Act: -0.1700
Data Index: 8713590 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.5146. Min Act: -0.1700
Data Index: 5238374 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.4833. Min Act: -0.1700
Data Index: 2489153 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.4521. Min Act: -0.1700
Data Index: 7735667 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.4208. Min Act: -0.1700
Data Index: 5584690 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.4208. Min Act: -0.1700
Data Index: 4275580 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.4208. Min Act: -0.1700
Data Index: 8713589 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.3583. Min Act: -0.1700
Data Index: 5584715 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.3583. Min Act: -0.1700
Data Index: 564031 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.3896. Min Act: -0.1700
Data Index: 2631956 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.2958. Min Act: -0.1700
Data Index: 1535651 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.3271. Min Act: -0.1700
Data Index: 5550777 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.2958. Min Act: -0.1700
Data Index: 99666 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.2646. Min Act: -0.1700
Data Index: 2631955 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.2333. Min Act: -0.1700
Data Index: 784679 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.2646. Min Act: -0.1700
Data Index: 3569837 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.2646. Min Act: -0.1700
Data Index: 8634061 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.2646. Min Act: -0.1700
Data Index: 5257429 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.2333. Min Act: -0.1700
Data Index: 256786 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5458. Min Range: -5.5458
Max Act: 5.2021. Min Act: -0.1700
Data Index: 8275258 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19