Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3718 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8479. Min Range: -7.8479
Max Act: 7.8479. Min Act: -0.1700
Data Index: 7928288 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8479. Min Range: -7.8479
Max Act: 7.7854. Min Act: -0.1700
Data Index: 1873504 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8479. Min Range: -7.8479
Max Act: 7.6604. Min Act: -0.1700
Data Index: 3831298 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8479. Min Range: -7.8479
Max Act: 7.5667. Min Act: -0.1700
Data Index: 5480687 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8479. Min Range: -7.8479
Max Act: 7.5354. Min Act: -0.1700
Data Index: 8583399 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8479. Min Range: -7.8479
Max Act: 7.5354. Min Act: -0.1700
Data Index: 1662163 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8479. Min Range: -7.8479
Max Act: 7.5354. Min Act: -0.1700
Data Index: 3036787 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8479. Min Range: -7.8479
Max Act: 7.5667. Min Act: -0.1700
Data Index: 1085179 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8479. Min Range: -7.8479
Max Act: 7.4417. Min Act: -0.1700
Data Index: 8012949 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8479. Min Range: -7.8479
Max Act: 7.3792. Min Act: -0.1700
Data Index: 1457288 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8479. Min Range: -7.8479
Max Act: 7.4104. Min Act: -0.1700
Data Index: 2793985 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8479. Min Range: -7.8479
Max Act: 7.4104. Min Act: -0.1700
Data Index: 6266055 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8479. Min Range: -7.8479
Max Act: 7.4104. Min Act: -0.1700
Data Index: 4090022 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8479. Min Range: -7.8479
Max Act: 7.3792. Min Act: -0.1700
Data Index: 5400309 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8479. Min Range: -7.8479
Max Act: 7.3167. Min Act: -0.1700
Data Index: 4470455 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8479. Min Range: -7.8479
Max Act: 7.1917. Min Act: -0.1700
Data Index: 3224449 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8479. Min Range: -7.8479
Max Act: 7.1917. Min Act: -0.1700
Data Index: 1584195 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8479. Min Range: -7.8479
Max Act: 7.0979. Min Act: -0.1700
Data Index: 7062950 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8479. Min Range: -7.8479
Max Act: 7.0979. Min Act: -0.1700
Data Index: 8496688 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8479. Min Range: -7.8479
Max Act: 7.0979. Min Act: -0.1700
Data Index: 3811572 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19