Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 899 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9224. Min Range: -5.9224
Max Act: 5.9224. Min Act: -0.1697
Data Index: 4999090 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9224. Min Range: -5.9224
Max Act: 5.9224. Min Act: -0.1700
Data Index: 4862014 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9224. Min Range: -5.9224
Max Act: 5.8912. Min Act: -0.1700
Data Index: 5511394 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9224. Min Range: -5.9224
Max Act: 5.7662. Min Act: -0.1700
Data Index: 6721882 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9224. Min Range: -5.9224
Max Act: 5.7662. Min Act: -0.1700
Data Index: 4601414 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9224. Min Range: -5.9224
Max Act: 5.7349. Min Act: -0.1700
Data Index: 8744014 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9224. Min Range: -5.9224
Max Act: 5.7349. Min Act: -0.1700
Data Index: 8820681 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9224. Min Range: -5.9224
Max Act: 5.7037. Min Act: -0.1700
Data Index: 1257864 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9224. Min Range: -5.9224
Max Act: 5.7349. Min Act: -0.1700
Data Index: 8719700 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9224. Min Range: -5.9224
Max Act: 5.7349. Min Act: -0.1700
Data Index: 7230260 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9224. Min Range: -5.9224
Max Act: 5.7349. Min Act: -0.1699
Data Index: 4967354 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9224. Min Range: -5.9224
Max Act: 5.7037. Min Act: -0.1700
Data Index: 3252213 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9224. Min Range: -5.9224
Max Act: 5.7037. Min Act: -0.1700
Data Index: 1823990 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9224. Min Range: -5.9224
Max Act: 5.7037. Min Act: -0.1700
Data Index: 4060233 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9224. Min Range: -5.9224
Max Act: 5.6724. Min Act: -0.1700
Data Index: 708427 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9224. Min Range: -5.9224
Max Act: 5.6724. Min Act: -0.1700
Data Index: 7002143 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9224. Min Range: -5.9224
Max Act: 5.6724. Min Act: -0.1698
Data Index: 1823994 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9224. Min Range: -5.9224
Max Act: 5.6412. Min Act: -0.1700
Data Index: 708431 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9224. Min Range: -5.9224
Max Act: 5.6412. Min Act: -0.1700
Data Index: 2212428 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9224. Min Range: -5.9224
Max Act: 5.6724. Min Act: -0.1700
Data Index: 4151017 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19