Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4450 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1118. Min Range: -6.1118
Max Act: 6.1118. Min Act: -0.1700
Data Index: 8139179 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1118. Min Range: -6.1118
Max Act: 5.9243. Min Act: -0.1700
Data Index: 6685457 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1118. Min Range: -6.1118
Max Act: 5.8618. Min Act: -0.1700
Data Index: 8536190 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1118. Min Range: -6.1118
Max Act: 5.7680. Min Act: -0.1700
Data Index: 1769996 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1118. Min Range: -6.1118
Max Act: 5.7368. Min Act: -0.1700
Data Index: 5906421 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1118. Min Range: -6.1118
Max Act: 5.6743. Min Act: -0.1700
Data Index: 3566040 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1118. Min Range: -6.1118
Max Act: 5.7055. Min Act: -0.1700
Data Index: 8349864 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1118. Min Range: -6.1118
Max Act: 5.6430. Min Act: -0.1700
Data Index: 27890 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1118. Min Range: -6.1118
Max Act: 5.6118. Min Act: -0.1700
Data Index: 692576 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1118. Min Range: -6.1118
Max Act: 5.5805. Min Act: -0.1700
Data Index: 4408290 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1118. Min Range: -6.1118
Max Act: 5.5493. Min Act: -0.1700
Data Index: 82614 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1118. Min Range: -6.1118
Max Act: 5.5805. Min Act: -0.1700
Data Index: 2131340 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1118. Min Range: -6.1118
Max Act: 5.5805. Min Act: -0.1700
Data Index: 5462842 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1118. Min Range: -6.1118
Max Act: 5.5493. Min Act: -0.1700
Data Index: 5280794 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1118. Min Range: -6.1118
Max Act: 5.5493. Min Act: -0.1700
Data Index: 2501030 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1118. Min Range: -6.1118
Max Act: 5.5180. Min Act: -0.1700
Data Index: 5190677 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1118. Min Range: -6.1118
Max Act: 5.5493. Min Act: -0.1700
Data Index: 3971139 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1118. Min Range: -6.1118
Max Act: 5.5180. Min Act: -0.1700
Data Index: 7475745 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1118. Min Range: -6.1118
Max Act: 5.5180. Min Act: -0.1700
Data Index: 7039462 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1118. Min Range: -6.1118
Max Act: 5.4555. Min Act: -0.1700
Data Index: 619735 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19