Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 572 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5555. Min Range: -9.5555
Max Act: 9.5555. Min Act: -0.1700
Data Index: 6188539 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5555. Min Range: -9.5555
Max Act: 9.4930. Min Act: -0.1700
Data Index: 2192189 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5555. Min Range: -9.5555
Max Act: 9.1180. Min Act: -0.1700
Data Index: 3872087 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5555. Min Range: -9.5555
Max Act: 9.1180. Min Act: -0.1700
Data Index: 8383216 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5555. Min Range: -9.5555
Max Act: 9.1180. Min Act: -0.1700
Data Index: 4671133 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5555. Min Range: -9.5555
Max Act: 9.0555. Min Act: -0.1700
Data Index: 4298848 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5555. Min Range: -9.5555
Max Act: 8.9930. Min Act: -0.1700
Data Index: 2630758 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5555. Min Range: -9.5555
Max Act: 8.9930. Min Act: -0.1700
Data Index: 7557183 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5555. Min Range: -9.5555
Max Act: 8.9930. Min Act: -0.1700
Data Index: 5038424 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5555. Min Range: -9.5555
Max Act: 8.9930. Min Act: -0.1700
Data Index: 4171454 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5555. Min Range: -9.5555
Max Act: 8.8680. Min Act: -0.1700
Data Index: 5366259 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5555. Min Range: -9.5555
Max Act: 8.9305. Min Act: -0.1700
Data Index: 4298835 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5555. Min Range: -9.5555
Max Act: 8.8680. Min Act: -0.1700
Data Index: 8040360 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5555. Min Range: -9.5555
Max Act: 8.9305. Min Act: -0.1700
Data Index: 2180581 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5555. Min Range: -9.5555
Max Act: 8.7430. Min Act: -0.1700
Data Index: 2397095 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5555. Min Range: -9.5555
Max Act: 8.7430. Min Act: -0.1700
Data Index: 1458226 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5555. Min Range: -9.5555
Max Act: 8.7430. Min Act: -0.1700
Data Index: 8621655 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5555. Min Range: -9.5555
Max Act: 8.7430. Min Act: -0.1700
Data Index: 4127058 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5555. Min Range: -9.5555
Max Act: 8.6805. Min Act: -0.1700
Data Index: 7557192 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5555. Min Range: -9.5555
Max Act: 8.6805. Min Act: -0.1700
Data Index: 7557187 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19