Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3139 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1441. Min Range: -6.1441
Max Act: 6.1441. Min Act: -0.1700
Data Index: 6487749 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1441. Min Range: -6.1441
Max Act: 6.0816. Min Act: -0.1699
Data Index: 6487761 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1441. Min Range: -6.1441
Max Act: 5.9566. Min Act: -0.1700
Data Index: 14956 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1441. Min Range: -6.1441
Max Act: 5.9253. Min Act: -0.1700
Data Index: 287630 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1441. Min Range: -6.1441
Max Act: 5.9253. Min Act: -0.1700
Data Index: 5100487 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1441. Min Range: -6.1441
Max Act: 5.8316. Min Act: -0.1700
Data Index: 479125 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1441. Min Range: -6.1441
Max Act: 5.8003. Min Act: -0.1700
Data Index: 6398682 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1441. Min Range: -6.1441
Max Act: 5.7691. Min Act: -0.1700
Data Index: 5832531 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1441. Min Range: -6.1441
Max Act: 5.7691. Min Act: -0.1700
Data Index: 7725729 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1441. Min Range: -6.1441
Max Act: 5.7691. Min Act: -0.1695
Data Index: 6294073 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1441. Min Range: -6.1441
Max Act: 5.7378. Min Act: -0.1700
Data Index: 123883 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1441. Min Range: -6.1441
Max Act: 5.6753. Min Act: -0.1700
Data Index: 5832527 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1441. Min Range: -6.1441
Max Act: 5.6753. Min Act: -0.1700
Data Index: 7388103 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1441. Min Range: -6.1441
Max Act: 5.6441. Min Act: -0.1699
Data Index: 8157812 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1441. Min Range: -6.1441
Max Act: 5.6441. Min Act: -0.1699
Data Index: 2024442 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1441. Min Range: -6.1441
Max Act: 5.6441. Min Act: -0.1699
Data Index: 8344577 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1441. Min Range: -6.1441
Max Act: 5.6441. Min Act: -0.1700
Data Index: 3533800 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1441. Min Range: -6.1441
Max Act: 5.6441. Min Act: -0.1700
Data Index: 1503265 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1441. Min Range: -6.1441
Max Act: 5.6128. Min Act: -0.1700
Data Index: 2992237 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1441. Min Range: -6.1441
Max Act: 5.5816. Min Act: -0.1699
Data Index: 973242 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19