Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3565 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4555. Min Range: -8.4555
Max Act: 8.4555. Min Act: -0.1700
Data Index: 4759515 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4555. Min Range: -8.4555
Max Act: 8.2055. Min Act: -0.1700
Data Index: 1220962 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4555. Min Range: -8.4555
Max Act: 8.1430. Min Act: -0.1700
Data Index: 700667 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4555. Min Range: -8.4555
Max Act: 8.0180. Min Act: -0.1700
Data Index: 6584242 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4555. Min Range: -8.4555
Max Act: 8.0180. Min Act: -0.1700
Data Index: 5949509 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4555. Min Range: -8.4555
Max Act: 8.0180. Min Act: -0.1700
Data Index: 164325 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4555. Min Range: -8.4555
Max Act: 7.8930. Min Act: -0.1700
Data Index: 6388210 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4555. Min Range: -8.4555
Max Act: 7.8930. Min Act: -0.1700
Data Index: 2205524 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4555. Min Range: -8.4555
Max Act: 7.8930. Min Act: -0.1700
Data Index: 5939831 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4555. Min Range: -8.4555
Max Act: 7.8930. Min Act: -0.1700
Data Index: 6939973 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4555. Min Range: -8.4555
Max Act: 7.8305. Min Act: -0.1700
Data Index: 7363626 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4555. Min Range: -8.4555
Max Act: 7.8930. Min Act: -0.1700
Data Index: 2580107 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4555. Min Range: -8.4555
Max Act: 7.7680. Min Act: -0.1700
Data Index: 4564833 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4555. Min Range: -8.4555
Max Act: 7.7680. Min Act: -0.1700
Data Index: 5919360 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4555. Min Range: -8.4555
Max Act: 7.7680. Min Act: -0.1700
Data Index: 8572023 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4555. Min Range: -8.4555
Max Act: 7.7680. Min Act: -0.1700
Data Index: 2981206 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4555. Min Range: -8.4555
Max Act: 7.7055. Min Act: -0.1700
Data Index: 7474209 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4555. Min Range: -8.4555
Max Act: 7.7055. Min Act: -0.1700
Data Index: 3784270 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4555. Min Range: -8.4555
Max Act: 7.7055. Min Act: -0.1700
Data Index: 5990877 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4555. Min Range: -8.4555
Max Act: 7.6743. Min Act: -0.1700
Data Index: 5300468 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19