Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2579 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9503. Min Range: -5.9503
Max Act: 5.9503. Min Act: -0.1700
Data Index: 7086251 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9503. Min Range: -5.9503
Max Act: 5.9191. Min Act: -0.1700
Data Index: 2807581 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9503. Min Range: -5.9503
Max Act: 5.6691. Min Act: -0.1700
Data Index: 7514934 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9503. Min Range: -5.9503
Max Act: 5.6378. Min Act: -0.1700
Data Index: 1719229 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9503. Min Range: -5.9503
Max Act: 5.6066. Min Act: -0.1700
Data Index: 189969 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9503. Min Range: -5.9503
Max Act: 5.5753. Min Act: -0.1700
Data Index: 5236878 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9503. Min Range: -5.9503
Max Act: 5.4816. Min Act: -0.1700
Data Index: 1719232 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9503. Min Range: -5.9503
Max Act: 5.5441. Min Act: -0.1700
Data Index: 1719248 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9503. Min Range: -5.9503
Max Act: 5.5128. Min Act: -0.1700
Data Index: 3020195 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9503. Min Range: -5.9503
Max Act: 5.5128. Min Act: -0.1700
Data Index: 8295346 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9503. Min Range: -5.9503
Max Act: 5.5128. Min Act: -0.1700
Data Index: 5236869 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9503. Min Range: -5.9503
Max Act: 5.4503. Min Act: -0.1700
Data Index: 7514928 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9503. Min Range: -5.9503
Max Act: 5.4503. Min Act: -0.1700
Data Index: 5124877 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9503. Min Range: -5.9503
Max Act: 5.4191. Min Act: -0.1700
Data Index: 8295344 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9503. Min Range: -5.9503
Max Act: 5.4191. Min Act: -0.1700
Data Index: 2807574 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9503. Min Range: -5.9503
Max Act: 5.4191. Min Act: -0.1700
Data Index: 7514932 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9503. Min Range: -5.9503
Max Act: 5.4191. Min Act: -0.1700
Data Index: 3052747 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9503. Min Range: -5.9503
Max Act: 5.3566. Min Act: -0.1700
Data Index: 5236870 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9503. Min Range: -5.9503
Max Act: 5.3878. Min Act: -0.1700
Data Index: 7879494 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9503. Min Range: -5.9503
Max Act: 5.3253. Min Act: -0.1700
Data Index: 189970 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19