Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3088 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6508. Min Range: -4.6508
Max Act: 4.6508. Min Act: -0.1700
Data Index: 3719995 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6508. Min Range: -4.6508
Max Act: 4.4633. Min Act: -0.1700
Data Index: 2109758 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6508. Min Range: -4.6508
Max Act: 4.3696. Min Act: -0.1700
Data Index: 1249041 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6508. Min Range: -4.6508
Max Act: 4.3696. Min Act: -0.1700
Data Index: 4422106 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6508. Min Range: -4.6508
Max Act: 4.4008. Min Act: -0.1700
Data Index: 4850278 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6508. Min Range: -4.6508
Max Act: 4.2445. Min Act: -0.1700
Data Index: 1785744 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6508. Min Range: -4.6508
Max Act: 4.3070. Min Act: -0.1700
Data Index: 7940870 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6508. Min Range: -4.6508
Max Act: 4.3383. Min Act: -0.1700
Data Index: 3262044 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6508. Min Range: -4.6508
Max Act: 4.2758. Min Act: -0.1700
Data Index: 6188954 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6508. Min Range: -4.6508
Max Act: 4.2758. Min Act: -0.1700
Data Index: 2090701 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6508. Min Range: -4.6508
Max Act: 4.2758. Min Act: -0.1700
Data Index: 3118542 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6508. Min Range: -4.6508
Max Act: 4.2445. Min Act: -0.1700
Data Index: 8828225 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6508. Min Range: -4.6508
Max Act: 4.2445. Min Act: -0.1700
Data Index: 6174019 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6508. Min Range: -4.6508
Max Act: 4.2445. Min Act: -0.1700
Data Index: 6102367 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6508. Min Range: -4.6508
Max Act: 4.2445. Min Act: -0.1700
Data Index: 2252536 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6508. Min Range: -4.6508
Max Act: 4.1820. Min Act: -0.1700
Data Index: 3790518 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6508. Min Range: -4.6508
Max Act: 4.1820. Min Act: -0.1700
Data Index: 3751500 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6508. Min Range: -4.6508
Max Act: 4.1820. Min Act: -0.1700
Data Index: 6095071 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6508. Min Range: -4.6508
Max Act: 4.1820. Min Act: -0.1700
Data Index: 6575468 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6508. Min Range: -4.6508
Max Act: 4.1508. Min Act: -0.1700
Data Index: 7942435 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19