Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2787 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2274. Min Range: -6.2274
Max Act: 6.2274. Min Act: -0.1700
Data Index: 664569 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2274. Min Range: -6.2274
Max Act: 5.8524. Min Act: -0.1700
Data Index: 2682264 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2274. Min Range: -6.2274
Max Act: 5.8524. Min Act: -0.1700
Data Index: 7551074 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2274. Min Range: -6.2274
Max Act: 5.8524. Min Act: -0.1700
Data Index: 7356136 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2274. Min Range: -6.2274
Max Act: 5.7274. Min Act: -0.1700
Data Index: 7417475 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2274. Min Range: -6.2274
Max Act: 5.7587. Min Act: -0.1700
Data Index: 5439471 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2274. Min Range: -6.2274
Max Act: 5.6024. Min Act: -0.1700
Data Index: 7757380 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2274. Min Range: -6.2274
Max Act: 5.5399. Min Act: -0.1700
Data Index: 2387473 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2274. Min Range: -6.2274
Max Act: 5.5712. Min Act: -0.1700
Data Index: 980722 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2274. Min Range: -6.2274
Max Act: 5.5399. Min Act: -0.1700
Data Index: 1655843 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2274. Min Range: -6.2274
Max Act: 5.5399. Min Act: -0.1700
Data Index: 7653458 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2274. Min Range: -6.2274
Max Act: 5.5399. Min Act: -0.1700
Data Index: 6517987 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2274. Min Range: -6.2274
Max Act: 5.5399. Min Act: -0.1700
Data Index: 3824118 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2274. Min Range: -6.2274
Max Act: 5.4774. Min Act: -0.1700
Data Index: 6950498 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2274. Min Range: -6.2274
Max Act: 5.5087. Min Act: -0.1700
Data Index: 3915880 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2274. Min Range: -6.2274
Max Act: 5.5087. Min Act: -0.1700
Data Index: 6618047 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2274. Min Range: -6.2274
Max Act: 5.4774. Min Act: -0.1700
Data Index: 1485132 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2274. Min Range: -6.2274
Max Act: 5.4774. Min Act: -0.1700
Data Index: 8740498 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2274. Min Range: -6.2274
Max Act: 5.4774. Min Act: -0.1700
Data Index: 5393236 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2274. Min Range: -6.2274
Max Act: 5.3837. Min Act: -0.1700
Data Index: 1310285 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19