Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3519 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6370. Min Range: -3.6370
Max Act: 3.6370. Min Act: -0.1700
Data Index: 2120674 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6370. Min Range: -3.6370
Max Act: 3.5901. Min Act: -0.1700
Data Index: 5091992 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6370. Min Range: -3.6370
Max Act: 3.5275. Min Act: -0.1700
Data Index: 2098535 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6370. Min Range: -3.6370
Max Act: 3.4805. Min Act: -0.1700
Data Index: 2897886 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6370. Min Range: -3.6370
Max Act: 3.4648. Min Act: -0.1700
Data Index: 1448908 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6370. Min Range: -3.6370
Max Act: 3.4648. Min Act: -0.1700
Data Index: 1379467 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6370. Min Range: -3.6370
Max Act: 3.4335. Min Act: -0.1700
Data Index: 6116825 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6370. Min Range: -3.6370
Max Act: 3.4178. Min Act: -0.1700
Data Index: 1740375 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6370. Min Range: -3.6370
Max Act: 3.4178. Min Act: -0.1700
Data Index: 804501 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6370. Min Range: -3.6370
Max Act: 3.4178. Min Act: -0.1700
Data Index: 2336181 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6370. Min Range: -3.6370
Max Act: 3.4021. Min Act: -0.1700
Data Index: 4920696 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6370. Min Range: -3.6370
Max Act: 3.3864. Min Act: -0.1700
Data Index: 4920694 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6370. Min Range: -3.6370
Max Act: 3.4021. Min Act: -0.1700
Data Index: 6264525 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6370. Min Range: -3.6370
Max Act: 3.3708. Min Act: -0.1700
Data Index: 1299212 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6370. Min Range: -3.6370
Max Act: 3.3708. Min Act: -0.1700
Data Index: 3405766 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6370. Min Range: -3.6370
Max Act: 3.3551. Min Act: -0.1700
Data Index: 1254267 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6370. Min Range: -3.6370
Max Act: 3.3394. Min Act: -0.1700
Data Index: 3254118 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6370. Min Range: -3.6370
Max Act: 3.3394. Min Act: -0.1700
Data Index: 3949691 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6370. Min Range: -3.6370
Max Act: 3.3394. Min Act: -0.1700
Data Index: 8359466 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6370. Min Range: -3.6370
Max Act: 3.3394. Min Act: -0.1700
Data Index: 4026862 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19