Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4626 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4231. Min Range: -6.4231
Max Act: 6.4231. Min Act: -0.1700
Data Index: 4473620 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4231. Min Range: -6.4231
Max Act: 6.3919. Min Act: -0.1700
Data Index: 1368293 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4231. Min Range: -6.4231
Max Act: 6.3919. Min Act: -0.1700
Data Index: 4161625 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4231. Min Range: -6.4231
Max Act: 6.3919. Min Act: -0.1700
Data Index: 1304857 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4231. Min Range: -6.4231
Max Act: 6.2981. Min Act: -0.1700
Data Index: 1711036 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4231. Min Range: -6.4231
Max Act: 6.2981. Min Act: -0.1700
Data Index: 1619228 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4231. Min Range: -6.4231
Max Act: 6.2981. Min Act: -0.1700
Data Index: 6699775 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4231. Min Range: -6.4231
Max Act: 6.2669. Min Act: -0.1700
Data Index: 3252333 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4231. Min Range: -6.4231
Max Act: 6.2981. Min Act: -0.1700
Data Index: 4790231 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4231. Min Range: -6.4231
Max Act: 6.2669. Min Act: -0.1700
Data Index: 7018138 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4231. Min Range: -6.4231
Max Act: 6.2669. Min Act: -0.1700
Data Index: 3694459 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4231. Min Range: -6.4231
Max Act: 6.2669. Min Act: -0.1700
Data Index: 6268416 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4231. Min Range: -6.4231
Max Act: 6.2981. Min Act: -0.1700
Data Index: 1673411 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4231. Min Range: -6.4231
Max Act: 6.2669. Min Act: -0.1700
Data Index: 5703926 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4231. Min Range: -6.4231
Max Act: 6.2356. Min Act: -0.1700
Data Index: 2916745 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4231. Min Range: -6.4231
Max Act: 6.2356. Min Act: -0.1700
Data Index: 530165 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4231. Min Range: -6.4231
Max Act: 6.2356. Min Act: -0.1700
Data Index: 5632850 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4231. Min Range: -6.4231
Max Act: 6.2356. Min Act: -0.1700
Data Index: 3336508 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4231. Min Range: -6.4231
Max Act: 6.2044. Min Act: -0.1700
Data Index: 4056579 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4231. Min Range: -6.4231
Max Act: 6.2044. Min Act: -0.1700
Data Index: 4349830 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19