Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 36 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0388. Min Range: -5.0388
Max Act: 5.0388. Min Act: -0.1700
Data Index: 4282148 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0388. Min Range: -5.0388
Max Act: 4.8513. Min Act: -0.1700
Data Index: 7596303 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0388. Min Range: -5.0388
Max Act: 4.8201. Min Act: -0.1700
Data Index: 634604 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0388. Min Range: -5.0388
Max Act: 4.7888. Min Act: -0.1700
Data Index: 1985798 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0388. Min Range: -5.0388
Max Act: 4.7576. Min Act: -0.1700
Data Index: 1600767 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0388. Min Range: -5.0388
Max Act: 4.6951. Min Act: -0.1700
Data Index: 7417186 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0388. Min Range: -5.0388
Max Act: 4.6638. Min Act: -0.1700
Data Index: 5125281 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0388. Min Range: -5.0388
Max Act: 4.6638. Min Act: -0.1700
Data Index: 6773860 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0388. Min Range: -5.0388
Max Act: 4.6638. Min Act: -0.1700
Data Index: 5269695 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0388. Min Range: -5.0388
Max Act: 4.6013. Min Act: -0.1700
Data Index: 1567108 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0388. Min Range: -5.0388
Max Act: 4.5701. Min Act: -0.1700
Data Index: 7107648 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0388. Min Range: -5.0388
Max Act: 4.5701. Min Act: -0.1700
Data Index: 7355067 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0388. Min Range: -5.0388
Max Act: 4.5701. Min Act: -0.1700
Data Index: 8484675 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0388. Min Range: -5.0388
Max Act: 4.5701. Min Act: -0.1700
Data Index: 3106820 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0388. Min Range: -5.0388
Max Act: 4.5701. Min Act: -0.1700
Data Index: 7606904 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0388. Min Range: -5.0388
Max Act: 4.5701. Min Act: -0.1700
Data Index: 2350 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0388. Min Range: -5.0388
Max Act: 4.5388. Min Act: -0.1700
Data Index: 1733319 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0388. Min Range: -5.0388
Max Act: 4.5388. Min Act: -0.1700
Data Index: 5193086 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0388. Min Range: -5.0388
Max Act: 4.5388. Min Act: -0.1700
Data Index: 1269611 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0388. Min Range: -5.0388
Max Act: 4.5701. Min Act: -0.1700
Data Index: 3751085 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19