Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2048 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 5.3526. Min Range: -5.3526
Max Act: 5.3526. Min Act: -0.1700
Data Index: 2960487 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3526. Min Range: -5.3526
Max Act: 5.2901. Min Act: -0.1700
Data Index: 6737828 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3526. Min Range: -5.3526
Max Act: 5.2589. Min Act: -0.1700
Data Index: 5464730 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3526. Min Range: -5.3526
Max Act: 5.2276. Min Act: -0.1700
Data Index: 685376 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3526. Min Range: -5.3526
Max Act: 5.1964. Min Act: -0.1700
Data Index: 4551871 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3526. Min Range: -5.3526
Max Act: 5.1964. Min Act: -0.1700
Data Index: 6737829 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3526. Min Range: -5.3526
Max Act: 5.2276. Min Act: -0.1700
Data Index: 2233584 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3526. Min Range: -5.3526
Max Act: 5.1651. Min Act: -0.1700
Data Index: 8410151 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3526. Min Range: -5.3526
Max Act: 5.1339. Min Act: -0.1700
Data Index: 2233582 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3526. Min Range: -5.3526
Max Act: 5.1339. Min Act: -0.1700
Data Index: 335823 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3526. Min Range: -5.3526
Max Act: 5.1026. Min Act: -0.1700
Data Index: 6675336 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3526. Min Range: -5.3526
Max Act: 5.1339. Min Act: -0.1700
Data Index: 7520564 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3526. Min Range: -5.3526
Max Act: 5.0714. Min Act: -0.1700
Data Index: 4520688 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3526. Min Range: -5.3526
Max Act: 5.1026. Min Act: -0.1700
Data Index: 2908970 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3526. Min Range: -5.3526
Max Act: 5.0714. Min Act: -0.1700
Data Index: 4755852 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3526. Min Range: -5.3526
Max Act: 5.0714. Min Act: -0.1700
Data Index: 8150369 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3526. Min Range: -5.3526
Max Act: 5.0401. Min Act: -0.1700
Data Index: 1383821 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3526. Min Range: -5.3526
Max Act: 5.0401. Min Act: -0.1700
Data Index: 3485544 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3526. Min Range: -5.3526
Max Act: 5.0089. Min Act: -0.1700
Data Index: 8444335 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3526. Min Range: -5.3526
Max Act: 5.0089. Min Act: -0.1700
Data Index: 3975245 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19