Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2451 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1558. Min Range: -5.1558
Max Act: 5.1558. Min Act: -0.1700
Data Index: 7039108 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1558. Min Range: -5.1558
Max Act: 5.1246. Min Act: -0.1700
Data Index: 941778 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1558. Min Range: -5.1558
Max Act: 5.0933. Min Act: -0.1700
Data Index: 7788485 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1558. Min Range: -5.1558
Max Act: 5.0933. Min Act: -0.1700
Data Index: 2597364 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.9683. Min Act: -0.1700
Data Index: 5801010 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.9371. Min Act: -0.1700
Data Index: 114559 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.9371. Min Act: -0.1700
Data Index: 3081669 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.9058. Min Act: -0.1700
Data Index: 3509529 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.9058. Min Act: -0.1700
Data Index: 7369435 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.9371. Min Act: -0.1700
Data Index: 1318451 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.9058. Min Act: -0.1700
Data Index: 4546430 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.8746. Min Act: -0.1700
Data Index: 1869115 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.8746. Min Act: -0.1700
Data Index: 7973480 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.8746. Min Act: -0.1700
Data Index: 3681495 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.8746. Min Act: -0.1700
Data Index: 3628306 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.8746. Min Act: -0.1700
Data Index: 379735 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.9058. Min Act: -0.1700
Data Index: 809872 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.8433. Min Act: -0.1700
Data Index: 3382099 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.8746. Min Act: -0.1700
Data Index: 3135393 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.8433. Min Act: -0.1700
Data Index: 7272402 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19