Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4364 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7824. Min Range: -5.7824
Max Act: 5.7824. Min Act: -0.1700
Data Index: 417813 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7824. Min Range: -5.7824
Max Act: 5.7824. Min Act: -0.1700
Data Index: 790769 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7824. Min Range: -5.7824
Max Act: 5.7512. Min Act: -0.1700
Data Index: 4606534 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7824. Min Range: -5.7824
Max Act: 5.7199. Min Act: -0.1700
Data Index: 737211 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7824. Min Range: -5.7824
Max Act: 5.7199. Min Act: -0.1700
Data Index: 6837966 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7824. Min Range: -5.7824
Max Act: 5.6574. Min Act: -0.1700
Data Index: 797644 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7824. Min Range: -5.7824
Max Act: 5.5949. Min Act: -0.1700
Data Index: 1903935 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7824. Min Range: -5.7824
Max Act: 5.5637. Min Act: -0.1700
Data Index: 36747 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7824. Min Range: -5.7824
Max Act: 5.5637. Min Act: -0.1700
Data Index: 256530 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7824. Min Range: -5.7824
Max Act: 5.5637. Min Act: -0.1700
Data Index: 80976 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7824. Min Range: -5.7824
Max Act: 5.5324. Min Act: -0.1700
Data Index: 7914980 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7824. Min Range: -5.7824
Max Act: 5.5324. Min Act: -0.1700
Data Index: 7685693 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7824. Min Range: -5.7824
Max Act: 5.5012. Min Act: -0.1700
Data Index: 1068072 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7824. Min Range: -5.7824
Max Act: 5.4699. Min Act: -0.1700
Data Index: 8793180 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7824. Min Range: -5.7824
Max Act: 5.5012. Min Act: -0.1700
Data Index: 2590200 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7824. Min Range: -5.7824
Max Act: 5.4387. Min Act: -0.1700
Data Index: 1025185 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7824. Min Range: -5.7824
Max Act: 5.4387. Min Act: -0.1700
Data Index: 8239053 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7824. Min Range: -5.7824
Max Act: 5.4387. Min Act: -0.1700
Data Index: 5467649 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7824. Min Range: -5.7824
Max Act: 5.4074. Min Act: -0.1700
Data Index: 3732253 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7824. Min Range: -5.7824
Max Act: 5.4074. Min Act: -0.1700
Data Index: 5760402 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19