Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2741 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2519. Min Range: -8.2519
Max Act: 8.2519. Min Act: -0.1700
Data Index: 7078180 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2519. Min Range: -8.2519
Max Act: 8.2519. Min Act: -0.1700
Data Index: 1429131 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2519. Min Range: -8.2519
Max Act: 8.0644. Min Act: -0.1700
Data Index: 1701555 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2519. Min Range: -8.2519
Max Act: 8.1269. Min Act: -0.1700
Data Index: 4694734 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2519. Min Range: -8.2519
Max Act: 8.0644. Min Act: -0.1700
Data Index: 841322 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2519. Min Range: -8.2519
Max Act: 8.0019. Min Act: -0.1700
Data Index: 5446221 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2519. Min Range: -8.2519
Max Act: 8.0644. Min Act: -0.1700
Data Index: 7414521 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2519. Min Range: -8.2519
Max Act: 8.0644. Min Act: -0.1700
Data Index: 4435485 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2519. Min Range: -8.2519
Max Act: 8.0644. Min Act: -0.1700
Data Index: 6564692 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2519. Min Range: -8.2519
Max Act: 8.0019. Min Act: -0.1699
Data Index: 4164435 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2519. Min Range: -8.2519
Max Act: 8.0019. Min Act: -0.1700
Data Index: 4656122 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2519. Min Range: -8.2519
Max Act: 7.9394. Min Act: -0.1700
Data Index: 7680300 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2519. Min Range: -8.2519
Max Act: 7.9394. Min Act: -0.1700
Data Index: 7551003 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2519. Min Range: -8.2519
Max Act: 7.9394. Min Act: -0.1700
Data Index: 1616296 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2519. Min Range: -8.2519
Max Act: 8.0019. Min Act: -0.1700
Data Index: 8605389 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2519. Min Range: -8.2519
Max Act: 7.9394. Min Act: -0.1700
Data Index: 5209735 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2519. Min Range: -8.2519
Max Act: 7.9394. Min Act: -0.1700
Data Index: 7264289 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2519. Min Range: -8.2519
Max Act: 7.9394. Min Act: -0.1700
Data Index: 5433179 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2519. Min Range: -8.2519
Max Act: 7.9394. Min Act: -0.1700
Data Index: 1835787 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2519. Min Range: -8.2519
Max Act: 7.8769. Min Act: -0.1700
Data Index: 5269430 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19