Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5512 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6651. Min Range: -6.6651
Max Act: 6.6651. Min Act: -0.1700
Data Index: 2371884 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6651. Min Range: -6.6651
Max Act: 6.2589. Min Act: -0.1700
Data Index: 8192296 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6651. Min Range: -6.6651
Max Act: 6.1651. Min Act: -0.1700
Data Index: 5801442 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6651. Min Range: -6.6651
Max Act: 6.1339. Min Act: -0.1700
Data Index: 474902 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6651. Min Range: -6.6651
Max Act: 6.0714. Min Act: -0.1700
Data Index: 6965491 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6651. Min Range: -6.6651
Max Act: 6.0401. Min Act: -0.1700
Data Index: 2504750 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6651. Min Range: -6.6651
Max Act: 5.9776. Min Act: -0.1700
Data Index: 2085409 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6651. Min Range: -6.6651
Max Act: 5.9776. Min Act: -0.1700
Data Index: 8304120 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6651. Min Range: -6.6651
Max Act: 5.9464. Min Act: -0.1700
Data Index: 8538488 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6651. Min Range: -6.6651
Max Act: 5.9464. Min Act: -0.1700
Data Index: 4170714 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6651. Min Range: -6.6651
Max Act: 5.9464. Min Act: -0.1700
Data Index: 700700 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6651. Min Range: -6.6651
Max Act: 5.9464. Min Act: -0.1700
Data Index: 2630962 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6651. Min Range: -6.6651
Max Act: 5.9464. Min Act: -0.1700
Data Index: 8657783 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6651. Min Range: -6.6651
Max Act: 5.9151. Min Act: -0.1700
Data Index: 8400094 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6651. Min Range: -6.6651
Max Act: 5.9151. Min Act: -0.1700
Data Index: 8325142 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6651. Min Range: -6.6651
Max Act: 5.9151. Min Act: -0.1700
Data Index: 4647447 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6651. Min Range: -6.6651
Max Act: 5.8526. Min Act: -0.1700
Data Index: 5072110 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6651. Min Range: -6.6651
Max Act: 5.8839. Min Act: -0.1700
Data Index: 2591100 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6651. Min Range: -6.6651
Max Act: 5.8839. Min Act: -0.1700
Data Index: 8289948 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6651. Min Range: -6.6651
Max Act: 5.8839. Min Act: -0.1700
Data Index: 6309251 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19