Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4980 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.9113. Min Act: -0.1700
Data Index: 2383269 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.7863. Min Act: -0.1700
Data Index: 3857940 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.7238. Min Act: -0.1700
Data Index: 8205784 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.7551. Min Act: -0.1700
Data Index: 6770556 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.7551. Min Act: -0.1700
Data Index: 7881302 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.7238. Min Act: -0.1700
Data Index: 1317405 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.7238. Min Act: -0.1700
Data Index: 1340232 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.7238. Min Act: -0.1700
Data Index: 7471766 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.7238. Min Act: -0.1700
Data Index: 2457318 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.6926. Min Act: -0.1700
Data Index: 4835893 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.7238. Min Act: -0.1700
Data Index: 114223 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.7238. Min Act: -0.1700
Data Index: 127844 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.6926. Min Act: -0.1700
Data Index: 8610934 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.6926. Min Act: -0.1700
Data Index: 3214202 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.7238. Min Act: -0.1700
Data Index: 4685530 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.6926. Min Act: -0.1700
Data Index: 7662643 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.6926. Min Act: -0.1700
Data Index: 2389859 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.6613. Min Act: -0.1700
Data Index: 7202146 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.6613. Min Act: -0.1700
Data Index: 430236 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.6613. Min Act: -0.1700
Data Index: 895258 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19