Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3522 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0644. Min Range: -3.0644
Max Act: 3.0644. Min Act: -0.1700
Data Index: 5205054 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0644. Min Range: -3.0644
Max Act: 3.0170. Min Act: -0.1700
Data Index: 4639953 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0644. Min Range: -3.0644
Max Act: 2.9854. Min Act: -0.1700
Data Index: 1913742 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0644. Min Range: -3.0644
Max Act: 2.9854. Min Act: -0.1700
Data Index: 4942178 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0644. Min Range: -3.0644
Max Act: 3.0012. Min Act: -0.1700
Data Index: 1597410 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0644. Min Range: -3.0644
Max Act: 2.9379. Min Act: -0.1700
Data Index: 6330479 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0644. Min Range: -3.0644
Max Act: 2.9379. Min Act: -0.1700
Data Index: 312866 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0644. Min Range: -3.0644
Max Act: 2.9221. Min Act: -0.1700
Data Index: 1127157 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0644. Min Range: -3.0644
Max Act: 2.9379. Min Act: -0.1700
Data Index: 1121551 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0644. Min Range: -3.0644
Max Act: 2.9221. Min Act: -0.1700
Data Index: 2390199 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0644. Min Range: -3.0644
Max Act: 2.9221. Min Act: -0.1700
Data Index: 2830682 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0644. Min Range: -3.0644
Max Act: 2.9063. Min Act: -0.1700
Data Index: 5889147 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0644. Min Range: -3.0644
Max Act: 2.9063. Min Act: -0.1700
Data Index: 3632811 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0644. Min Range: -3.0644
Max Act: 2.9063. Min Act: -0.1700
Data Index: 1897920 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0644. Min Range: -3.0644
Max Act: 2.8904. Min Act: -0.1700
Data Index: 2507014 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0644. Min Range: -3.0644
Max Act: 2.8745. Min Act: -0.1700
Data Index: 4486891 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0644. Min Range: -3.0644
Max Act: 2.8586. Min Act: -0.1700
Data Index: 4797828 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0644. Min Range: -3.0644
Max Act: 2.8428. Min Act: -0.1700
Data Index: 8656668 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0644. Min Range: -3.0644
Max Act: 2.8269. Min Act: -0.1700
Data Index: 4148594 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0644. Min Range: -3.0644
Max Act: 2.8269. Min Act: -0.1700
Data Index: 5213526 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19