Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5182 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1613. Min Range: -6.1613
Max Act: 6.1613. Min Act: -0.1700
Data Index: 4257921 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1613. Min Range: -6.1613
Max Act: 6.0988. Min Act: -0.1700
Data Index: 7012713 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1613. Min Range: -6.1613
Max Act: 5.9425. Min Act: -0.1700
Data Index: 734973 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1613. Min Range: -6.1613
Max Act: 5.8488. Min Act: -0.1700
Data Index: 5558426 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1613. Min Range: -6.1613
Max Act: 5.8175. Min Act: -0.1700
Data Index: 3678922 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1613. Min Range: -6.1613
Max Act: 5.7863. Min Act: -0.1700
Data Index: 4203145 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1613. Min Range: -6.1613
Max Act: 5.7550. Min Act: -0.1700
Data Index: 3040362 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1613. Min Range: -6.1613
Max Act: 5.7863. Min Act: -0.1700
Data Index: 6628371 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1613. Min Range: -6.1613
Max Act: 5.7550. Min Act: -0.1700
Data Index: 3135463 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1613. Min Range: -6.1613
Max Act: 5.7238. Min Act: -0.1700
Data Index: 4095566 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1613. Min Range: -6.1613
Max Act: 5.6925. Min Act: -0.1700
Data Index: 1418410 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1613. Min Range: -6.1613
Max Act: 5.6613. Min Act: -0.1700
Data Index: 4045152 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1613. Min Range: -6.1613
Max Act: 5.5988. Min Act: -0.1700
Data Index: 8586854 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1613. Min Range: -6.1613
Max Act: 5.6300. Min Act: -0.1700
Data Index: 1051036 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1613. Min Range: -6.1613
Max Act: 5.6300. Min Act: -0.1700
Data Index: 6763870 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1613. Min Range: -6.1613
Max Act: 5.6300. Min Act: -0.1700
Data Index: 1394436 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1613. Min Range: -6.1613
Max Act: 5.5988. Min Act: -0.1700
Data Index: 149165 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1613. Min Range: -6.1613
Max Act: 5.5363. Min Act: -0.1700
Data Index: 4243821 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1613. Min Range: -6.1613
Max Act: 5.5675. Min Act: -0.1700
Data Index: 442298 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1613. Min Range: -6.1613
Max Act: 5.5675. Min Act: -0.1700
Data Index: 5667015 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19