Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4515 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4414. Min Range: -6.4414
Max Act: 6.4414. Min Act: -0.1700
Data Index: 8286259 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4414. Min Range: -6.4414
Max Act: 6.4102. Min Act: -0.1700
Data Index: 1057945 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4414. Min Range: -6.4414
Max Act: 6.4102. Min Act: -0.1700
Data Index: 2831519 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4414. Min Range: -6.4414
Max Act: 6.3789. Min Act: -0.1700
Data Index: 4180608 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4414. Min Range: -6.4414
Max Act: 6.3789. Min Act: -0.1700
Data Index: 3311305 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4414. Min Range: -6.4414
Max Act: 6.3477. Min Act: -0.1700
Data Index: 8217200 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4414. Min Range: -6.4414
Max Act: 6.3789. Min Act: -0.1700
Data Index: 753877 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4414. Min Range: -6.4414
Max Act: 6.3477. Min Act: -0.1700
Data Index: 7897936 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4414. Min Range: -6.4414
Max Act: 6.3477. Min Act: -0.1700
Data Index: 2789711 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4414. Min Range: -6.4414
Max Act: 6.3164. Min Act: -0.1700
Data Index: 3423871 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4414. Min Range: -6.4414
Max Act: 6.2852. Min Act: -0.1700
Data Index: 1492575 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4414. Min Range: -6.4414
Max Act: 6.3477. Min Act: -0.1700
Data Index: 3123636 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4414. Min Range: -6.4414
Max Act: 6.3164. Min Act: -0.1699
Data Index: 7285118 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4414. Min Range: -6.4414
Max Act: 6.2852. Min Act: -0.1700
Data Index: 837349 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4414. Min Range: -6.4414
Max Act: 6.2852. Min Act: -0.1700
Data Index: 7344592 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4414. Min Range: -6.4414
Max Act: 6.2852. Min Act: -0.1700
Data Index: 3270610 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4414. Min Range: -6.4414
Max Act: 6.2852. Min Act: -0.1700
Data Index: 8157041 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4414. Min Range: -6.4414
Max Act: 6.2852. Min Act: -0.1700
Data Index: 4572769 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4414. Min Range: -6.4414
Max Act: 6.2539. Min Act: -0.1700
Data Index: 2612221 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4414. Min Range: -6.4414
Max Act: 6.2539. Min Act: -0.1700
Data Index: 7344593 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19