Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 647 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8362. Min Range: -5.8362
Max Act: 5.8362. Min Act: -0.1700
Data Index: 4324304 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8362. Min Range: -5.8362
Max Act: 5.8050. Min Act: -0.1700
Data Index: 281506 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8362. Min Range: -5.8362
Max Act: 5.7737. Min Act: -0.1700
Data Index: 7262264 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8362. Min Range: -5.8362
Max Act: 5.6800. Min Act: -0.1700
Data Index: 2189550 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8362. Min Range: -5.8362
Max Act: 5.6487. Min Act: -0.1700
Data Index: 6992507 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8362. Min Range: -5.8362
Max Act: 5.6175. Min Act: -0.1700
Data Index: 1687017 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8362. Min Range: -5.8362
Max Act: 5.5862. Min Act: -0.1700
Data Index: 821100 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8362. Min Range: -5.8362
Max Act: 5.6175. Min Act: -0.1700
Data Index: 8501668 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8362. Min Range: -5.8362
Max Act: 5.5862. Min Act: -0.1700
Data Index: 1207831 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8362. Min Range: -5.8362
Max Act: 5.5550. Min Act: -0.1700
Data Index: 2275270 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8362. Min Range: -5.8362
Max Act: 5.5550. Min Act: -0.1700
Data Index: 533154 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8362. Min Range: -5.8362
Max Act: 5.5862. Min Act: -0.1700
Data Index: 4077436 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8362. Min Range: -5.8362
Max Act: 5.5237. Min Act: -0.1700
Data Index: 536023 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8362. Min Range: -5.8362
Max Act: 5.5237. Min Act: -0.1700
Data Index: 6085559 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8362. Min Range: -5.8362
Max Act: 5.4925. Min Act: -0.1700
Data Index: 1395629 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8362. Min Range: -5.8362
Max Act: 5.4300. Min Act: -0.1700
Data Index: 637828 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8362. Min Range: -5.8362
Max Act: 5.4612. Min Act: -0.1700
Data Index: 8559876 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8362. Min Range: -5.8362
Max Act: 5.4612. Min Act: -0.1700
Data Index: 6447191 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8362. Min Range: -5.8362
Max Act: 5.4612. Min Act: -0.1700
Data Index: 2892806 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8362. Min Range: -5.8362
Max Act: 5.4300. Min Act: -0.1700
Data Index: 3450329 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19