Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2547 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3599. Min Range: -8.3599
Max Act: 8.3599. Min Act: -0.1700
Data Index: 4343902 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3599. Min Range: -8.3599
Max Act: 8.3599. Min Act: -0.1700
Data Index: 8535363 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3599. Min Range: -8.3599
Max Act: 8.3599. Min Act: -0.1700
Data Index: 1917478 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3599. Min Range: -8.3599
Max Act: 8.1099. Min Act: -0.1700
Data Index: 8206222 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3599. Min Range: -8.3599
Max Act: 8.0474. Min Act: -0.1700
Data Index: 2047650 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3599. Min Range: -8.3599
Max Act: 7.9224. Min Act: -0.1700
Data Index: 1227024 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3599. Min Range: -8.3599
Max Act: 7.7974. Min Act: -0.1700
Data Index: 965342 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3599. Min Range: -8.3599
Max Act: 7.7974. Min Act: -0.1700
Data Index: 2190375 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3599. Min Range: -8.3599
Max Act: 7.7349. Min Act: -0.1700
Data Index: 7739163 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3599. Min Range: -8.3599
Max Act: 7.7349. Min Act: -0.1700
Data Index: 3773419 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3599. Min Range: -8.3599
Max Act: 7.7662. Min Act: -0.1700
Data Index: 8287208 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3599. Min Range: -8.3599
Max Act: 7.7349. Min Act: -0.1700
Data Index: 7299218 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3599. Min Range: -8.3599
Max Act: 7.6724. Min Act: -0.1700
Data Index: 5761419 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3599. Min Range: -8.3599
Max Act: 7.6724. Min Act: -0.1700
Data Index: 2596512 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3599. Min Range: -8.3599
Max Act: 7.6724. Min Act: -0.1700
Data Index: 1547216 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3599. Min Range: -8.3599
Max Act: 7.6724. Min Act: -0.1700
Data Index: 8480917 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3599. Min Range: -8.3599
Max Act: 7.6724. Min Act: -0.1700
Data Index: 239040 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3599. Min Range: -8.3599
Max Act: 7.6412. Min Act: -0.1700
Data Index: 2398444 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3599. Min Range: -8.3599
Max Act: 7.6099. Min Act: -0.1700
Data Index: 7398409 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3599. Min Range: -8.3599
Max Act: 7.6099. Min Act: -0.1700
Data Index: 1300030 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19