Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5035 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5960. Min Range: -3.5960
Max Act: 3.5960. Min Act: -0.1700
Data Index: 6685493 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5960. Min Range: -3.5960
Max Act: 3.5647. Min Act: -0.1700
Data Index: 6834000 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5960. Min Range: -3.5960
Max Act: 3.1725. Min Act: -0.1700
Data Index: 3279265 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5960. Min Range: -3.5960
Max Act: 3.1095. Min Act: -0.1700
Data Index: 4491764 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5960. Min Range: -3.5960
Max Act: 3.0937. Min Act: -0.1700
Data Index: 769033 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5960. Min Range: -3.5960
Max Act: 3.0622. Min Act: -0.1700
Data Index: 1473328 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5960. Min Range: -3.5960
Max Act: 3.0622. Min Act: -0.1700
Data Index: 4257619 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5960. Min Range: -3.5960
Max Act: 3.0622. Min Act: -0.1700
Data Index: 2700958 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5960. Min Range: -3.5960
Max Act: 3.0306. Min Act: -0.1700
Data Index: 1159230 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5960. Min Range: -3.5960
Max Act: 3.0464. Min Act: -0.1700
Data Index: 8073996 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5960. Min Range: -3.5960
Max Act: 3.0464. Min Act: -0.1700
Data Index: 4788854 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5960. Min Range: -3.5960
Max Act: 2.9832. Min Act: -0.1700
Data Index: 3030850 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5960. Min Range: -3.5960
Max Act: 2.9832. Min Act: -0.1700
Data Index: 5414559 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5960. Min Range: -3.5960
Max Act: 2.9516. Min Act: -0.1700
Data Index: 2396328 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5960. Min Range: -3.5960
Max Act: 2.9674. Min Act: -0.1700
Data Index: 1714035 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5960. Min Range: -3.5960
Max Act: 2.9674. Min Act: -0.1700
Data Index: 7213072 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5960. Min Range: -3.5960
Max Act: 2.9516. Min Act: -0.1700
Data Index: 6365313 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5960. Min Range: -3.5960
Max Act: 2.9674. Min Act: -0.1700
Data Index: 2492189 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5960. Min Range: -3.5960
Max Act: 2.9357. Min Act: -0.1700
Data Index: 8673999 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5960. Min Range: -3.5960
Max Act: 2.9674. Min Act: -0.1700
Data Index: 8109885 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19