Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2413 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9462. Min Range: -4.9462
Max Act: 4.9462. Min Act: -0.1700
Data Index: 5488979 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9462. Min Range: -4.9462
Max Act: 4.8837. Min Act: -0.1700
Data Index: 2541302 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9462. Min Range: -4.9462
Max Act: 4.8837. Min Act: -0.1700
Data Index: 1916183 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9462. Min Range: -4.9462
Max Act: 4.8837. Min Act: -0.1700
Data Index: 2128139 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9462. Min Range: -4.9462
Max Act: 4.8212. Min Act: -0.1700
Data Index: 8801404 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9462. Min Range: -4.9462
Max Act: 4.8212. Min Act: -0.1700
Data Index: 557608 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9462. Min Range: -4.9462
Max Act: 4.8212. Min Act: -0.1700
Data Index: 3056565 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9462. Min Range: -4.9462
Max Act: 4.8212. Min Act: -0.1700
Data Index: 7539448 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9462. Min Range: -4.9462
Max Act: 4.7899. Min Act: -0.1700
Data Index: 3397855 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9462. Min Range: -4.9462
Max Act: 4.8212. Min Act: -0.1700
Data Index: 7573657 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9462. Min Range: -4.9462
Max Act: 4.7899. Min Act: -0.1700
Data Index: 1990951 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9462. Min Range: -4.9462
Max Act: 4.7899. Min Act: -0.1700
Data Index: 3989032 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9462. Min Range: -4.9462
Max Act: 4.7899. Min Act: -0.1700
Data Index: 8569317 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9462. Min Range: -4.9462
Max Act: 4.7899. Min Act: -0.1700
Data Index: 6439851 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9462. Min Range: -4.9462
Max Act: 4.7587. Min Act: -0.1700
Data Index: 3166959 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9462. Min Range: -4.9462
Max Act: 4.7899. Min Act: -0.1700
Data Index: 1380428 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9462. Min Range: -4.9462
Max Act: 4.7587. Min Act: -0.1700
Data Index: 5565591 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9462. Min Range: -4.9462
Max Act: 4.7274. Min Act: -0.1700
Data Index: 4536338 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9462. Min Range: -4.9462
Max Act: 4.7587. Min Act: -0.1699
Data Index: 2624291 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9462. Min Range: -4.9462
Max Act: 4.7587. Min Act: -0.1700
Data Index: 7638818 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19