Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1052 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.5112. Min Act: -0.1700
Data Index: 5311848 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.0737. Min Act: -0.1700
Data Index: 3351707 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.0112. Min Act: -0.1700
Data Index: 3364848 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5112. Min Range: -4.5112
Max Act: 3.9174. Min Act: -0.1700
Data Index: 5345777 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5112. Min Range: -4.5112
Max Act: 3.9487. Min Act: -0.1700
Data Index: 4513697 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5112. Min Range: -4.5112
Max Act: 3.9174. Min Act: -0.1700
Data Index: 7447008 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5112. Min Range: -4.5112
Max Act: 3.9174. Min Act: -0.1700
Data Index: 4457816 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5112. Min Range: -4.5112
Max Act: 3.8861. Min Act: -0.1700
Data Index: 7964563 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5112. Min Range: -4.5112
Max Act: 3.8549. Min Act: -0.1700
Data Index: 4311119 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5112. Min Range: -4.5112
Max Act: 3.8236. Min Act: -0.1700
Data Index: 4422655 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5112. Min Range: -4.5112
Max Act: 3.8236. Min Act: -0.1700
Data Index: 3321744 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5112. Min Range: -4.5112
Max Act: 3.8236. Min Act: -0.1700
Data Index: 2952149 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5112. Min Range: -4.5112
Max Act: 3.8236. Min Act: -0.1700
Data Index: 4196934 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5112. Min Range: -4.5112
Max Act: 3.7923. Min Act: -0.1700
Data Index: 1799037 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5112. Min Range: -4.5112
Max Act: 3.8236. Min Act: -0.1700
Data Index: 496869 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5112. Min Range: -4.5112
Max Act: 3.7923. Min Act: -0.1700
Data Index: 336584 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5112. Min Range: -4.5112
Max Act: 3.7923. Min Act: -0.1700
Data Index: 7630771 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5112. Min Range: -4.5112
Max Act: 3.7610. Min Act: -0.1700
Data Index: 1032516 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5112. Min Range: -4.5112
Max Act: 3.7610. Min Act: -0.1700
Data Index: 5716432 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5112. Min Range: -4.5112
Max Act: 3.7923. Min Act: -0.1700
Data Index: 414714 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19