Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2444 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7907. Min Range: -6.7907
Max Act: 6.7907. Min Act: -0.1700
Data Index: 66118 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7907. Min Range: -6.7907
Max Act: 6.7594. Min Act: -0.1700
Data Index: 2100649 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7907. Min Range: -6.7907
Max Act: 6.7282. Min Act: -0.1700
Data Index: 7671144 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7907. Min Range: -6.7907
Max Act: 6.6344. Min Act: -0.1700
Data Index: 20677 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7907. Min Range: -6.7907
Max Act: 6.6032. Min Act: -0.1700
Data Index: 1900940 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7907. Min Range: -6.7907
Max Act: 6.6032. Min Act: -0.1700
Data Index: 6111124 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7907. Min Range: -6.7907
Max Act: 6.6032. Min Act: -0.1700
Data Index: 3952221 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7907. Min Range: -6.7907
Max Act: 6.5719. Min Act: -0.1700
Data Index: 3308445 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7907. Min Range: -6.7907
Max Act: 6.5719. Min Act: -0.1700
Data Index: 1741052 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7907. Min Range: -6.7907
Max Act: 6.5719. Min Act: -0.1700
Data Index: 7494 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7907. Min Range: -6.7907
Max Act: 6.5719. Min Act: -0.1700
Data Index: 1952625 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7907. Min Range: -6.7907
Max Act: 6.5407. Min Act: -0.1700
Data Index: 2894460 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7907. Min Range: -6.7907
Max Act: 6.5407. Min Act: -0.1700
Data Index: 8432865 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7907. Min Range: -6.7907
Max Act: 6.5094. Min Act: -0.1700
Data Index: 4204864 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7907. Min Range: -6.7907
Max Act: 6.5094. Min Act: -0.1700
Data Index: 8466032 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7907. Min Range: -6.7907
Max Act: 6.4157. Min Act: -0.1700
Data Index: 1361466 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7907. Min Range: -6.7907
Max Act: 6.4157. Min Act: -0.1700
Data Index: 4775373 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7907. Min Range: -6.7907
Max Act: 6.4157. Min Act: -0.1700
Data Index: 6319185 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7907. Min Range: -6.7907
Max Act: 6.3844. Min Act: -0.1700
Data Index: 2047191 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7907. Min Range: -6.7907
Max Act: 6.3844. Min Act: -0.1700
Data Index: 5095568 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19