Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3996 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0613. Min Range: -5.0613
Max Act: 5.0613. Min Act: -0.1700
Data Index: 7850690 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0613. Min Range: -5.0613
Max Act: 5.0301. Min Act: -0.1700
Data Index: 4135109 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0613. Min Range: -5.0613
Max Act: 4.9988. Min Act: -0.1700
Data Index: 7124189 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0613. Min Range: -5.0613
Max Act: 4.9676. Min Act: -0.1700
Data Index: 2642132 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0613. Min Range: -5.0613
Max Act: 4.8738. Min Act: -0.1700
Data Index: 441854 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0613. Min Range: -5.0613
Max Act: 4.8426. Min Act: -0.1700
Data Index: 3498929 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0613. Min Range: -5.0613
Max Act: 4.7801. Min Act: -0.1700
Data Index: 7810112 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0613. Min Range: -5.0613
Max Act: 4.7801. Min Act: -0.1700
Data Index: 3141432 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0613. Min Range: -5.0613
Max Act: 4.7801. Min Act: -0.1700
Data Index: 8190778 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0613. Min Range: -5.0613
Max Act: 4.7801. Min Act: -0.1700
Data Index: 5798939 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0613. Min Range: -5.0613
Max Act: 4.7488. Min Act: -0.1700
Data Index: 8322673 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0613. Min Range: -5.0613
Max Act: 4.7488. Min Act: -0.1700
Data Index: 8421711 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0613. Min Range: -5.0613
Max Act: 4.7176. Min Act: -0.1700
Data Index: 1203808 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0613. Min Range: -5.0613
Max Act: 4.6863. Min Act: -0.1700
Data Index: 1623365 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0613. Min Range: -5.0613
Max Act: 4.6863. Min Act: -0.1700
Data Index: 8411719 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0613. Min Range: -5.0613
Max Act: 4.6551. Min Act: -0.1700
Data Index: 3917414 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0613. Min Range: -5.0613
Max Act: 4.6551. Min Act: -0.1700
Data Index: 6689821 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0613. Min Range: -5.0613
Max Act: 4.6551. Min Act: -0.1700
Data Index: 7299816 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0613. Min Range: -5.0613
Max Act: 4.6551. Min Act: -0.1700
Data Index: 2528241 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0613. Min Range: -5.0613
Max Act: 4.6551. Min Act: -0.1700
Data Index: 3795611 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19