Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3519 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.2446. Min Act: -0.1700
Data Index: 8053747 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.2133. Min Act: -0.1700
Data Index: 6746242 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.2133. Min Act: -0.1700
Data Index: 1223701 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.1821. Min Act: -0.1700
Data Index: 995373 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.1821. Min Act: -0.1700
Data Index: 6981623 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.2133. Min Act: -0.1700
Data Index: 2117638 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.1196. Min Act: -0.1700
Data Index: 7456772 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.1508. Min Act: -0.1700
Data Index: 5728967 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.1196. Min Act: -0.1700
Data Index: 3753287 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.1196. Min Act: -0.1700
Data Index: 3645497 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.1196. Min Act: -0.1700
Data Index: 957981 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.1196. Min Act: -0.1700
Data Index: 1523076 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.1508. Min Act: -0.1700
Data Index: 6227516 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.0883. Min Act: -0.1700
Data Index: 3605730 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.0883. Min Act: -0.1700
Data Index: 8162141 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.0883. Min Act: -0.1700
Data Index: 7676941 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.0571. Min Act: -0.1700
Data Index: 1156403 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.0883. Min Act: -0.1700
Data Index: 7171293 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.0571. Min Act: -0.1700
Data Index: 290123 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2446. Min Range: -6.2446
Max Act: 6.0571. Min Act: -0.1700
Data Index: 3409382 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19