Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 907 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9478. Min Range: -3.9478
Max Act: 3.9478. Min Act: -0.1700
Data Index: 8297041 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9478. Min Range: -3.9478
Max Act: 3.5567. Min Act: -0.1700
Data Index: 7469910 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9478. Min Range: -3.9478
Max Act: 3.4941. Min Act: -0.1700
Data Index: 3853239 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9478. Min Range: -3.9478
Max Act: 3.4628. Min Act: -0.1700
Data Index: 4258891 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9478. Min Range: -3.9478
Max Act: 3.4157. Min Act: -0.1700
Data Index: 3210685 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9478. Min Range: -3.9478
Max Act: 3.3844. Min Act: -0.1700
Data Index: 5092136 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9478. Min Range: -3.9478
Max Act: 3.3530. Min Act: -0.1700
Data Index: 7498830 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9478. Min Range: -3.9478
Max Act: 3.3373. Min Act: -0.1700
Data Index: 2277824 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9478. Min Range: -3.9478
Max Act: 3.3216. Min Act: -0.1700
Data Index: 3984473 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9478. Min Range: -3.9478
Max Act: 3.3059. Min Act: -0.1700
Data Index: 4712732 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9478. Min Range: -3.9478
Max Act: 3.3373. Min Act: -0.1700
Data Index: 5510053 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9478. Min Range: -3.9478
Max Act: 3.3373. Min Act: -0.1700
Data Index: 7526490 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9478. Min Range: -3.9478
Max Act: 3.3216. Min Act: -0.1700
Data Index: 2620919 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9478. Min Range: -3.9478
Max Act: 3.3373. Min Act: -0.1700
Data Index: 4703513 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9478. Min Range: -3.9478
Max Act: 3.3216. Min Act: -0.1700
Data Index: 8556738 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9478. Min Range: -3.9478
Max Act: 3.3216. Min Act: -0.1700
Data Index: 6364688 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9478. Min Range: -3.9478
Max Act: 3.3373. Min Act: -0.1700
Data Index: 5221213 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9478. Min Range: -3.9478
Max Act: 3.3059. Min Act: -0.1700
Data Index: 4210705 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9478. Min Range: -3.9478
Max Act: 3.3059. Min Act: -0.1700
Data Index: 3341955 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9478. Min Range: -3.9478
Max Act: 3.2902. Min Act: -0.1700
Data Index: 1262666 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19