Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4049 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5762. Min Range: -6.5762
Max Act: 6.5762. Min Act: -0.1700
Data Index: 2988010 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5762. Min Range: -6.5762
Max Act: 6.4200. Min Act: -0.1700
Data Index: 498375 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5762. Min Range: -6.5762
Max Act: 6.3887. Min Act: -0.1700
Data Index: 6869639 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5762. Min Range: -6.5762
Max Act: 6.2950. Min Act: -0.1700
Data Index: 181116 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5762. Min Range: -6.5762
Max Act: 6.2637. Min Act: -0.1700
Data Index: 933993 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5762. Min Range: -6.5762
Max Act: 6.2950. Min Act: -0.1700
Data Index: 6936154 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5762. Min Range: -6.5762
Max Act: 6.2325. Min Act: -0.1700
Data Index: 6024445 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5762. Min Range: -6.5762
Max Act: 6.2325. Min Act: -0.1700
Data Index: 7506300 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5762. Min Range: -6.5762
Max Act: 6.1700. Min Act: -0.1700
Data Index: 4945037 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5762. Min Range: -6.5762
Max Act: 6.1387. Min Act: -0.1700
Data Index: 1383713 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5762. Min Range: -6.5762
Max Act: 6.1075. Min Act: -0.1700
Data Index: 6099858 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5762. Min Range: -6.5762
Max Act: 6.0762. Min Act: -0.1700
Data Index: 3556942 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5762. Min Range: -6.5762
Max Act: 6.0450. Min Act: -0.1700
Data Index: 4143879 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5762. Min Range: -6.5762
Max Act: 6.0450. Min Act: -0.1700
Data Index: 4511434 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5762. Min Range: -6.5762
Max Act: 6.0450. Min Act: -0.1700
Data Index: 4846675 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5762. Min Range: -6.5762
Max Act: 5.9825. Min Act: -0.1700
Data Index: 3211983 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5762. Min Range: -6.5762
Max Act: 5.9825. Min Act: -0.1700
Data Index: 2348763 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5762. Min Range: -6.5762
Max Act: 5.9825. Min Act: -0.1700
Data Index: 483449 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5762. Min Range: -6.5762
Max Act: 5.9825. Min Act: -0.1700
Data Index: 4390778 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5762. Min Range: -6.5762
Max Act: 5.9200. Min Act: -0.1700
Data Index: 5140495 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19