Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5605 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3002. Min Range: -6.3002
Max Act: 6.3002. Min Act: -0.1700
Data Index: 4173107 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3002. Min Range: -6.3002
Max Act: 6.2690. Min Act: -0.1700
Data Index: 1879456 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3002. Min Range: -6.3002
Max Act: 6.2065. Min Act: -0.1700
Data Index: 4248195 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3002. Min Range: -6.3002
Max Act: 6.2065. Min Act: -0.1700
Data Index: 4173106 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3002. Min Range: -6.3002
Max Act: 6.1440. Min Act: -0.1700
Data Index: 2562741 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3002. Min Range: -6.3002
Max Act: 6.0190. Min Act: -0.1700
Data Index: 7956879 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3002. Min Range: -6.3002
Max Act: 5.9877. Min Act: -0.1700
Data Index: 8251463 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3002. Min Range: -6.3002
Max Act: 5.9877. Min Act: -0.1700
Data Index: 4564812 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3002. Min Range: -6.3002
Max Act: 5.9252. Min Act: -0.1700
Data Index: 3809256 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3002. Min Range: -6.3002
Max Act: 5.9252. Min Act: -0.1700
Data Index: 2692616 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3002. Min Range: -6.3002
Max Act: 5.8627. Min Act: -0.1700
Data Index: 8251464 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3002. Min Range: -6.3002
Max Act: 5.8627. Min Act: -0.1700
Data Index: 707193 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3002. Min Range: -6.3002
Max Act: 5.8627. Min Act: -0.1700
Data Index: 8251465 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3002. Min Range: -6.3002
Max Act: 5.8627. Min Act: -0.1700
Data Index: 1385688 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3002. Min Range: -6.3002
Max Act: 5.8315. Min Act: -0.1700
Data Index: 1472556 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3002. Min Range: -6.3002
Max Act: 5.8315. Min Act: -0.1700
Data Index: 7891815 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3002. Min Range: -6.3002
Max Act: 5.7690. Min Act: -0.1700
Data Index: 3363613 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3002. Min Range: -6.3002
Max Act: 5.7690. Min Act: -0.1700
Data Index: 1385690 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3002. Min Range: -6.3002
Max Act: 5.7377. Min Act: -0.1700
Data Index: 3809257 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3002. Min Range: -6.3002
Max Act: 5.7377. Min Act: -0.1700
Data Index: 1472560 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19