Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1173 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9317. Min Range: -8.9317
Max Act: 8.9317. Min Act: -0.1700
Data Index: 7538066 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9317. Min Range: -8.9317
Max Act: 8.9317. Min Act: -0.1700
Data Index: 407657 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9317. Min Range: -8.9317
Max Act: 8.8692. Min Act: -0.1700
Data Index: 3701379 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9317. Min Range: -8.9317
Max Act: 8.8067. Min Act: -0.1700
Data Index: 3961868 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9317. Min Range: -8.9317
Max Act: 8.7442. Min Act: -0.1700
Data Index: 8051460 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9317. Min Range: -8.9317
Max Act: 8.6192. Min Act: -0.1700
Data Index: 271004 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9317. Min Range: -8.9317
Max Act: 8.4942. Min Act: -0.1700
Data Index: 8812647 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9317. Min Range: -8.9317
Max Act: 8.4942. Min Act: -0.1700
Data Index: 8802978 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9317. Min Range: -8.9317
Max Act: 8.4942. Min Act: -0.1700
Data Index: 1829183 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9317. Min Range: -8.9317
Max Act: 8.4317. Min Act: -0.1700
Data Index: 6142062 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9317. Min Range: -8.9317
Max Act: 8.4317. Min Act: -0.1700
Data Index: 7074571 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9317. Min Range: -8.9317
Max Act: 8.3067. Min Act: -0.1700
Data Index: 7572133 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9317. Min Range: -8.9317
Max Act: 8.3692. Min Act: -0.1700
Data Index: 3585753 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9317. Min Range: -8.9317
Max Act: 8.3067. Min Act: -0.1700
Data Index: 6577705 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9317. Min Range: -8.9317
Max Act: 8.3067. Min Act: -0.1700
Data Index: 750901 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9317. Min Range: -8.9317
Max Act: 8.3067. Min Act: -0.1700
Data Index: 8056394 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9317. Min Range: -8.9317
Max Act: 8.2442. Min Act: -0.1700
Data Index: 7383487 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9317. Min Range: -8.9317
Max Act: 8.3067. Min Act: -0.1700
Data Index: 4354351 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9317. Min Range: -8.9317
Max Act: 8.3067. Min Act: -0.1700
Data Index: 4516634 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9317. Min Range: -8.9317
Max Act: 8.3067. Min Act: -0.1700
Data Index: 1806495 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19