Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3040 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0627. Min Range: -6.0627
Max Act: 6.0627. Min Act: -0.1700
Data Index: 4481021 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.8440. Min Act: -0.1700
Data Index: 8027634 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.8127. Min Act: -0.1700
Data Index: 140258 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.8127. Min Act: -0.1700
Data Index: 4311111 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.6877. Min Act: -0.1700
Data Index: 7067215 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.6565. Min Act: -0.1700
Data Index: 522992 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.6565. Min Act: -0.1700
Data Index: 8538687 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.6252. Min Act: -0.1700
Data Index: 7655600 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.5940. Min Act: -0.1700
Data Index: 5306912 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.5627. Min Act: -0.1700
Data Index: 5639939 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.5627. Min Act: -0.1700
Data Index: 864789 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.5315. Min Act: -0.1700
Data Index: 4373456 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.5627. Min Act: -0.1700
Data Index: 4008726 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.5315. Min Act: -0.1700
Data Index: 5707949 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.5315. Min Act: -0.1700
Data Index: 3608129 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.5315. Min Act: -0.1700
Data Index: 6968997 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.5002. Min Act: -0.1700
Data Index: 4221918 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.5002. Min Act: -0.1700
Data Index: 3716470 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.4690. Min Act: -0.1700
Data Index: 1129429 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.4690. Min Act: -0.1700
Data Index: 1788602 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19