Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2954 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8627. Min Range: -8.8627
Max Act: 8.8627. Min Act: -0.1700
Data Index: 4056766 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8627. Min Range: -8.8627
Max Act: 8.8627. Min Act: -0.1700
Data Index: 2477777 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8627. Min Range: -8.8627
Max Act: 8.7377. Min Act: -0.1700
Data Index: 6148587 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8627. Min Range: -8.8627
Max Act: 8.6752. Min Act: -0.1700
Data Index: 6818157 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8627. Min Range: -8.8627
Max Act: 8.5502. Min Act: -0.1700
Data Index: 343231 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8627. Min Range: -8.8627
Max Act: 8.4877. Min Act: -0.1700
Data Index: 63061 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8627. Min Range: -8.8627
Max Act: 8.4252. Min Act: -0.1700
Data Index: 2369770 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8627. Min Range: -8.8627
Max Act: 8.4252. Min Act: -0.1700
Data Index: 1125137 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8627. Min Range: -8.8627
Max Act: 8.4252. Min Act: -0.1700
Data Index: 2637636 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8627. Min Range: -8.8627
Max Act: 8.4252. Min Act: -0.1700
Data Index: 674561 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8627. Min Range: -8.8627
Max Act: 8.4252. Min Act: -0.1700
Data Index: 6818156 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8627. Min Range: -8.8627
Max Act: 8.3627. Min Act: -0.1700
Data Index: 6722367 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8627. Min Range: -8.8627
Max Act: 8.3627. Min Act: -0.1700
Data Index: 4025361 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8627. Min Range: -8.8627
Max Act: 8.3002. Min Act: -0.1700
Data Index: 6682060 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8627. Min Range: -8.8627
Max Act: 8.3002. Min Act: -0.1700
Data Index: 6003486 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8627. Min Range: -8.8627
Max Act: 8.3002. Min Act: -0.1700
Data Index: 6751682 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8627. Min Range: -8.8627
Max Act: 8.2377. Min Act: -0.1700
Data Index: 7330748 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8627. Min Range: -8.8627
Max Act: 8.3002. Min Act: -0.1700
Data Index: 6569132 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8627. Min Range: -8.8627
Max Act: 8.2377. Min Act: -0.1700
Data Index: 3724662 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8627. Min Range: -8.8627
Max Act: 8.1752. Min Act: -0.1700
Data Index: 7142062 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19