Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3684 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5463. Min Range: -8.5463
Max Act: 8.5463. Min Act: -0.1700
Data Index: 2551282 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5463. Min Range: -8.5463
Max Act: 8.4838. Min Act: -0.1700
Data Index: 3412852 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5463. Min Range: -8.5463
Max Act: 8.2963. Min Act: -0.1700
Data Index: 1663757 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5463. Min Range: -8.5463
Max Act: 8.1713. Min Act: -0.1700
Data Index: 3466159 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5463. Min Range: -8.5463
Max Act: 7.9213. Min Act: -0.1700
Data Index: 3107175 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5463. Min Range: -8.5463
Max Act: 7.8588. Min Act: -0.1700
Data Index: 5587320 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5463. Min Range: -8.5463
Max Act: 7.8588. Min Act: -0.1700
Data Index: 6490807 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5463. Min Range: -8.5463
Max Act: 7.8588. Min Act: -0.1700
Data Index: 5960044 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5463. Min Range: -8.5463
Max Act: 7.8588. Min Act: -0.1700
Data Index: 1371899 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5463. Min Range: -8.5463
Max Act: 7.8588. Min Act: -0.1700
Data Index: 395355 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5463. Min Range: -8.5463
Max Act: 7.8276. Min Act: -0.1700
Data Index: 4609268 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5463. Min Range: -8.5463
Max Act: 7.7963. Min Act: -0.1700
Data Index: 4628967 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5463. Min Range: -8.5463
Max Act: 7.7963. Min Act: -0.1700
Data Index: 1478144 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5463. Min Range: -8.5463
Max Act: 7.7338. Min Act: -0.1700
Data Index: 1394160 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5463. Min Range: -8.5463
Max Act: 7.7338. Min Act: -0.1700
Data Index: 3898387 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5463. Min Range: -8.5463
Max Act: 7.7026. Min Act: -0.1700
Data Index: 1727197 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5463. Min Range: -8.5463
Max Act: 7.7338. Min Act: -0.1700
Data Index: 4778794 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5463. Min Range: -8.5463
Max Act: 7.6713. Min Act: -0.1700
Data Index: 861715 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5463. Min Range: -8.5463
Max Act: 7.6713. Min Act: -0.1700
Data Index: 5191450 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5463. Min Range: -8.5463
Max Act: 7.6401. Min Act: -0.1700
Data Index: 2500282 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19