Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4390 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8825. Min Range: -5.8825
Max Act: 5.8825. Min Act: -0.1700
Data Index: 3401685 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8825. Min Range: -5.8825
Max Act: 5.8200. Min Act: -0.1700
Data Index: 3241344 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8825. Min Range: -5.8825
Max Act: 5.7575. Min Act: -0.1700
Data Index: 2900848 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8825. Min Range: -5.8825
Max Act: 5.7262. Min Act: -0.1700
Data Index: 5997668 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8825. Min Range: -5.8825
Max Act: 5.7262. Min Act: -0.1700
Data Index: 5819892 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8825. Min Range: -5.8825
Max Act: 5.7575. Min Act: -0.1700
Data Index: 3175371 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8825. Min Range: -5.8825
Max Act: 5.6950. Min Act: -0.1700
Data Index: 1862090 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8825. Min Range: -5.8825
Max Act: 5.6950. Min Act: -0.1700
Data Index: 7681994 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8825. Min Range: -5.8825
Max Act: 5.6637. Min Act: -0.1700
Data Index: 5972480 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8825. Min Range: -5.8825
Max Act: 5.6637. Min Act: -0.1700
Data Index: 3227890 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8825. Min Range: -5.8825
Max Act: 5.6637. Min Act: -0.1700
Data Index: 7133028 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8825. Min Range: -5.8825
Max Act: 5.6637. Min Act: -0.1700
Data Index: 1693811 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8825. Min Range: -5.8825
Max Act: 5.6325. Min Act: -0.1700
Data Index: 5995328 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8825. Min Range: -5.8825
Max Act: 5.6012. Min Act: -0.1700
Data Index: 5380637 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8825. Min Range: -5.8825
Max Act: 5.6012. Min Act: -0.1700
Data Index: 5170976 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8825. Min Range: -5.8825
Max Act: 5.5700. Min Act: -0.1700
Data Index: 4608678 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8825. Min Range: -5.8825
Max Act: 5.5700. Min Act: -0.1700
Data Index: 7510387 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8825. Min Range: -5.8825
Max Act: 5.5700. Min Act: -0.1700
Data Index: 5133607 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8825. Min Range: -5.8825
Max Act: 5.5387. Min Act: -0.1700
Data Index: 4562405 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8825. Min Range: -5.8825
Max Act: 5.5387. Min Act: -0.1700
Data Index: 3594722 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19