Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5824 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8872. Min Range: -4.8872
Max Act: 4.8872. Min Act: -0.1700
Data Index: 7963691 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8872. Min Range: -4.8872
Max Act: 4.8872. Min Act: -0.1700
Data Index: 1552687 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8872. Min Range: -4.8872
Max Act: 4.8247. Min Act: -0.1700
Data Index: 7288688 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8872. Min Range: -4.8872
Max Act: 4.8560. Min Act: -0.1700
Data Index: 24497 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8872. Min Range: -4.8872
Max Act: 4.6685. Min Act: -0.1700
Data Index: 6173206 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8872. Min Range: -4.8872
Max Act: 4.6997. Min Act: -0.1700
Data Index: 4188413 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8872. Min Range: -4.8872
Max Act: 4.6685. Min Act: -0.1700
Data Index: 5261671 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8872. Min Range: -4.8872
Max Act: 4.6685. Min Act: -0.1700
Data Index: 932712 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8872. Min Range: -4.8872
Max Act: 4.6685. Min Act: -0.1700
Data Index: 5018006 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8872. Min Range: -4.8872
Max Act: 4.6685. Min Act: -0.1700
Data Index: 4962343 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8872. Min Range: -4.8872
Max Act: 4.6372. Min Act: -0.1700
Data Index: 4918427 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8872. Min Range: -4.8872
Max Act: 4.6060. Min Act: -0.1700
Data Index: 7209763 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8872. Min Range: -4.8872
Max Act: 4.6060. Min Act: -0.1700
Data Index: 5608655 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8872. Min Range: -4.8872
Max Act: 4.6060. Min Act: -0.1700
Data Index: 4486006 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8872. Min Range: -4.8872
Max Act: 4.6060. Min Act: -0.1700
Data Index: 6668084 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8872. Min Range: -4.8872
Max Act: 4.5747. Min Act: -0.1700
Data Index: 8294454 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8872. Min Range: -4.8872
Max Act: 4.5747. Min Act: -0.1700
Data Index: 4625006 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8872. Min Range: -4.8872
Max Act: 4.6060. Min Act: -0.1700
Data Index: 4547398 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8872. Min Range: -4.8872
Max Act: 4.5747. Min Act: -0.1700
Data Index: 4006771 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8872. Min Range: -4.8872
Max Act: 4.5747. Min Act: -0.1700
Data Index: 4469701 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19