Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 170 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2826. Min Range: -6.2826
Max Act: 6.2826. Min Act: -0.1700
Data Index: 2260510 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2826. Min Range: -6.2826
Max Act: 6.2201. Min Act: -0.1700
Data Index: 8179394 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2826. Min Range: -6.2826
Max Act: 6.0638. Min Act: -0.1700
Data Index: 5829838 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2826. Min Range: -6.2826
Max Act: 6.0013. Min Act: -0.1700
Data Index: 8071002 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2826. Min Range: -6.2826
Max Act: 6.0013. Min Act: -0.1700
Data Index: 6776494 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2826. Min Range: -6.2826
Max Act: 5.9388. Min Act: -0.1700
Data Index: 48855 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2826. Min Range: -6.2826
Max Act: 5.9388. Min Act: -0.1700
Data Index: 1761558 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2826. Min Range: -6.2826
Max Act: 5.9076. Min Act: -0.1700
Data Index: 6111357 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2826. Min Range: -6.2826
Max Act: 5.9388. Min Act: -0.1700
Data Index: 7818549 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2826. Min Range: -6.2826
Max Act: 5.9388. Min Act: -0.1700
Data Index: 860892 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2826. Min Range: -6.2826
Max Act: 5.9076. Min Act: -0.1700
Data Index: 1285068 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2826. Min Range: -6.2826
Max Act: 5.9076. Min Act: -0.1700
Data Index: 583249 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2826. Min Range: -6.2826
Max Act: 5.9076. Min Act: -0.1700
Data Index: 152316 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2826. Min Range: -6.2826
Max Act: 5.8763. Min Act: -0.1700
Data Index: 1690829 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2826. Min Range: -6.2826
Max Act: 5.8763. Min Act: -0.1700
Data Index: 1928427 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2826. Min Range: -6.2826
Max Act: 5.8763. Min Act: -0.1700
Data Index: 381739 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2826. Min Range: -6.2826
Max Act: 5.8763. Min Act: -0.1700
Data Index: 3855908 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2826. Min Range: -6.2826
Max Act: 5.8451. Min Act: -0.1700
Data Index: 6348613 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2826. Min Range: -6.2826
Max Act: 5.8451. Min Act: -0.1700
Data Index: 7102493 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2826. Min Range: -6.2826
Max Act: 5.8138. Min Act: -0.1700
Data Index: 6818488 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19