Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 502 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9850. Min Range: -2.9850
Max Act: 2.9850. Min Act: -0.1700
Data Index: 8496845 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9850. Min Range: -2.9850
Max Act: 2.9692. Min Act: -0.1700
Data Index: 5617099 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9850. Min Range: -2.9850
Max Act: 2.9217. Min Act: -0.1700
Data Index: 5299310 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9850. Min Range: -2.9850
Max Act: 2.8900. Min Act: -0.1700
Data Index: 5730949 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9850. Min Range: -2.9850
Max Act: 2.8900. Min Act: -0.1700
Data Index: 3531824 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9850. Min Range: -2.9850
Max Act: 2.8741. Min Act: -0.1700
Data Index: 6495314 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9850. Min Range: -2.9850
Max Act: 2.8423. Min Act: -0.1700
Data Index: 5647891 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9850. Min Range: -2.9850
Max Act: 2.8264. Min Act: -0.1700
Data Index: 4555864 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9850. Min Range: -2.9850
Max Act: 2.7946. Min Act: -0.1700
Data Index: 895646 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9850. Min Range: -2.9850
Max Act: 2.7946. Min Act: -0.1700
Data Index: 4477921 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9850. Min Range: -2.9850
Max Act: 2.7627. Min Act: -0.1700
Data Index: 8778607 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9850. Min Range: -2.9850
Max Act: 2.7627. Min Act: -0.1700
Data Index: 7697255 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9850. Min Range: -2.9850
Max Act: 2.7787. Min Act: -0.1700
Data Index: 5548343 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9850. Min Range: -2.9850
Max Act: 2.7627. Min Act: -0.1700
Data Index: 3807783 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9850. Min Range: -2.9850
Max Act: 2.7308. Min Act: -0.1700
Data Index: 8562196 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9850. Min Range: -2.9850
Max Act: 2.7467. Min Act: -0.1700
Data Index: 4685410 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9850. Min Range: -2.9850
Max Act: 2.7148. Min Act: -0.1700
Data Index: 2846163 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9850. Min Range: -2.9850
Max Act: 2.7148. Min Act: -0.1700
Data Index: 215462 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9850. Min Range: -2.9850
Max Act: 2.7148. Min Act: -0.1700
Data Index: 2492667 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9850. Min Range: -2.9850
Max Act: 2.6988. Min Act: -0.1700
Data Index: 7928488 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19