Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 745 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2587. Min Range: -5.2587
Max Act: 5.2587. Min Act: -0.1700
Data Index: 7380893 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2587. Min Range: -5.2587
Max Act: 5.2275. Min Act: -0.1700
Data Index: 5726534 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2587. Min Range: -5.2587
Max Act: 5.1337. Min Act: -0.1700
Data Index: 4815736 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2587. Min Range: -5.2587
Max Act: 5.0712. Min Act: -0.1700
Data Index: 3351183 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2587. Min Range: -5.2587
Max Act: 5.0087. Min Act: -0.1700
Data Index: 1040606 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2587. Min Range: -5.2587
Max Act: 5.0087. Min Act: -0.1700
Data Index: 7271335 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2587. Min Range: -5.2587
Max Act: 4.9462. Min Act: -0.1700
Data Index: 499535 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2587. Min Range: -5.2587
Max Act: 4.9150. Min Act: -0.1700
Data Index: 4976778 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2587. Min Range: -5.2587
Max Act: 4.9775. Min Act: -0.1700
Data Index: 7259033 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2587. Min Range: -5.2587
Max Act: 4.9462. Min Act: -0.1700
Data Index: 3493314 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2587. Min Range: -5.2587
Max Act: 4.9775. Min Act: -0.1700
Data Index: 4491338 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2587. Min Range: -5.2587
Max Act: 4.9775. Min Act: -0.1700
Data Index: 3782427 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2587. Min Range: -5.2587
Max Act: 4.8837. Min Act: -0.1700
Data Index: 3797339 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2587. Min Range: -5.2587
Max Act: 4.9150. Min Act: -0.1700
Data Index: 1863521 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2587. Min Range: -5.2587
Max Act: 4.9150. Min Act: -0.1700
Data Index: 1178623 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2587. Min Range: -5.2587
Max Act: 4.9150. Min Act: -0.1700
Data Index: 4410806 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2587. Min Range: -5.2587
Max Act: 4.9150. Min Act: -0.1700
Data Index: 1645096 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2587. Min Range: -5.2587
Max Act: 4.8837. Min Act: -0.1700
Data Index: 893316 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2587. Min Range: -5.2587
Max Act: 4.8525. Min Act: -0.1700
Data Index: 2724024 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2587. Min Range: -5.2587
Max Act: 4.8525. Min Act: -0.1700
Data Index: 7157800 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19