Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2740 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4640. Min Range: -7.4640
Max Act: 7.4640. Min Act: -0.1700
Data Index: 5390432 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4640. Min Range: -7.4640
Max Act: 7.1827. Min Act: -0.1700
Data Index: 5751827 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4640. Min Range: -7.4640
Max Act: 6.9952. Min Act: -0.1700
Data Index: 5060786 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4640. Min Range: -7.4640
Max Act: 6.9327. Min Act: -0.1700
Data Index: 5830674 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4640. Min Range: -7.4640
Max Act: 6.9015. Min Act: -0.1700
Data Index: 392406 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4640. Min Range: -7.4640
Max Act: 6.9015. Min Act: -0.1700
Data Index: 7723349 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4640. Min Range: -7.4640
Max Act: 6.8390. Min Act: -0.1700
Data Index: 1554375 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4640. Min Range: -7.4640
Max Act: 6.8390. Min Act: -0.1700
Data Index: 1357032 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4640. Min Range: -7.4640
Max Act: 6.7765. Min Act: -0.1700
Data Index: 717688 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4640. Min Range: -7.4640
Max Act: 6.7765. Min Act: -0.1698
Data Index: 5390431 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4640. Min Range: -7.4640
Max Act: 6.7452. Min Act: -0.1700
Data Index: 1424721 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4640. Min Range: -7.4640
Max Act: 6.7140. Min Act: -0.1700
Data Index: 7841495 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4640. Min Range: -7.4640
Max Act: 6.7140. Min Act: -0.1700
Data Index: 3579911 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4640. Min Range: -7.4640
Max Act: 6.7452. Min Act: -0.1700
Data Index: 3200791 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4640. Min Range: -7.4640
Max Act: 6.6827. Min Act: -0.1700
Data Index: 7813067 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4640. Min Range: -7.4640
Max Act: 6.6827. Min Act: -0.1697
Data Index: 4932921 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4640. Min Range: -7.4640
Max Act: 6.6827. Min Act: -0.1700
Data Index: 3881193 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4640. Min Range: -7.4640
Max Act: 6.6515. Min Act: -0.1700
Data Index: 807331 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4640. Min Range: -7.4640
Max Act: 6.6202. Min Act: -0.1700
Data Index: 1556344 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4640. Min Range: -7.4640
Max Act: 6.5890. Min Act: -0.1700
Data Index: 255133 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19