Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3307 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0809. Min Range: -7.0809
Max Act: 7.0809. Min Act: -0.1700
Data Index: 2976090 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0809. Min Range: -7.0809
Max Act: 6.4871. Min Act: -0.1700
Data Index: 3520048 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0809. Min Range: -7.0809
Max Act: 6.3621. Min Act: -0.1700
Data Index: 8645838 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0809. Min Range: -7.0809
Max Act: 6.2059. Min Act: -0.1700
Data Index: 247103 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0809. Min Range: -7.0809
Max Act: 6.2059. Min Act: -0.1700
Data Index: 2243791 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0809. Min Range: -7.0809
Max Act: 6.1434. Min Act: -0.1700
Data Index: 5916558 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0809. Min Range: -7.0809
Max Act: 6.0496. Min Act: -0.1700
Data Index: 5729364 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0809. Min Range: -7.0809
Max Act: 6.0184. Min Act: -0.1700
Data Index: 1668112 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0809. Min Range: -7.0809
Max Act: 5.9559. Min Act: -0.1700
Data Index: 4915993 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0809. Min Range: -7.0809
Max Act: 5.9559. Min Act: -0.1700
Data Index: 3277057 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0809. Min Range: -7.0809
Max Act: 5.9871. Min Act: -0.1700
Data Index: 5701889 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0809. Min Range: -7.0809
Max Act: 5.9871. Min Act: -0.1700
Data Index: 6809745 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0809. Min Range: -7.0809
Max Act: 5.9246. Min Act: -0.1700
Data Index: 2002865 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0809. Min Range: -7.0809
Max Act: 5.9246. Min Act: -0.1700
Data Index: 5875808 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0809. Min Range: -7.0809
Max Act: 5.9559. Min Act: -0.1700
Data Index: 615303 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0809. Min Range: -7.0809
Max Act: 5.8934. Min Act: -0.1700
Data Index: 5541958 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0809. Min Range: -7.0809
Max Act: 5.8934. Min Act: -0.1700
Data Index: 4121511 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0809. Min Range: -7.0809
Max Act: 5.8309. Min Act: -0.1700
Data Index: 512948 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0809. Min Range: -7.0809
Max Act: 5.8621. Min Act: -0.1700
Data Index: 7587589 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0809. Min Range: -7.0809
Max Act: 5.8309. Min Act: -0.1700
Data Index: 4877053 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19