Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2700 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0467. Min Range: -8.0467
Max Act: 8.0467. Min Act: -0.1700
Data Index: 592536 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0467. Min Range: -8.0467
Max Act: 7.7342. Min Act: -0.1700
Data Index: 6989287 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0467. Min Range: -8.0467
Max Act: 7.7654. Min Act: -0.1700
Data Index: 3501425 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0467. Min Range: -8.0467
Max Act: 7.7342. Min Act: -0.1700
Data Index: 2246253 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0467. Min Range: -8.0467
Max Act: 7.7342. Min Act: -0.1700
Data Index: 4426877 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0467. Min Range: -8.0467
Max Act: 7.7029. Min Act: -0.1700
Data Index: 802302 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0467. Min Range: -8.0467
Max Act: 7.6717. Min Act: -0.1700
Data Index: 4546216 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0467. Min Range: -8.0467
Max Act: 7.6404. Min Act: -0.1700
Data Index: 7699538 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0467. Min Range: -8.0467
Max Act: 7.6404. Min Act: -0.1700
Data Index: 7472271 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0467. Min Range: -8.0467
Max Act: 7.5779. Min Act: -0.1700
Data Index: 6962479 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0467. Min Range: -8.0467
Max Act: 7.5467. Min Act: -0.1700
Data Index: 7472272 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0467. Min Range: -8.0467
Max Act: 7.5154. Min Act: -0.1700
Data Index: 5304669 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0467. Min Range: -8.0467
Max Act: 7.5154. Min Act: -0.1700
Data Index: 44956 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0467. Min Range: -8.0467
Max Act: 7.5154. Min Act: -0.1700
Data Index: 3849805 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0467. Min Range: -8.0467
Max Act: 7.4217. Min Act: -0.1700
Data Index: 7691666 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0467. Min Range: -8.0467
Max Act: 7.4217. Min Act: -0.1700
Data Index: 4021672 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0467. Min Range: -8.0467
Max Act: 7.3904. Min Act: -0.1700
Data Index: 8552589 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0467. Min Range: -8.0467
Max Act: 7.3592. Min Act: -0.1700
Data Index: 912243 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0467. Min Range: -8.0467
Max Act: 7.3592. Min Act: -0.1700
Data Index: 5490653 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0467. Min Range: -8.0467
Max Act: 7.3279. Min Act: -0.1700
Data Index: 240365 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19