Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4900 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8423. Min Range: -5.8423
Max Act: 5.8423. Min Act: -0.1700
Data Index: 2552469 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8423. Min Range: -5.8423
Max Act: 5.7485. Min Act: -0.1700
Data Index: 4652709 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8423. Min Range: -5.8423
Max Act: 5.6548. Min Act: -0.1700
Data Index: 2845768 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8423. Min Range: -5.8423
Max Act: 5.5923. Min Act: -0.1700
Data Index: 6435152 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8423. Min Range: -5.8423
Max Act: 5.5923. Min Act: -0.1700
Data Index: 7153752 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8423. Min Range: -5.8423
Max Act: 5.5298. Min Act: -0.1700
Data Index: 1129613 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8423. Min Range: -5.8423
Max Act: 5.4985. Min Act: -0.1700
Data Index: 2151517 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8423. Min Range: -5.8423
Max Act: 5.4673. Min Act: -0.1700
Data Index: 6452040 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8423. Min Range: -5.8423
Max Act: 5.4673. Min Act: -0.1700
Data Index: 3815433 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8423. Min Range: -5.8423
Max Act: 5.4360. Min Act: -0.1700
Data Index: 6668136 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8423. Min Range: -5.8423
Max Act: 5.4048. Min Act: -0.1700
Data Index: 2605173 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8423. Min Range: -5.8423
Max Act: 5.4673. Min Act: -0.1700
Data Index: 1428290 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8423. Min Range: -5.8423
Max Act: 5.4673. Min Act: -0.1700
Data Index: 6292519 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8423. Min Range: -5.8423
Max Act: 5.4360. Min Act: -0.1700
Data Index: 4916226 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8423. Min Range: -5.8423
Max Act: 5.4048. Min Act: -0.1700
Data Index: 2114595 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8423. Min Range: -5.8423
Max Act: 5.3735. Min Act: -0.1700
Data Index: 8290525 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8423. Min Range: -5.8423
Max Act: 5.3735. Min Act: -0.1700
Data Index: 2679135 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8423. Min Range: -5.8423
Max Act: 5.3735. Min Act: -0.1700
Data Index: 165693 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8423. Min Range: -5.8423
Max Act: 5.3735. Min Act: -0.1700
Data Index: 4064463 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8423. Min Range: -5.8423
Max Act: 5.3423. Min Act: -0.1700
Data Index: 406155 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19