Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 175 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1257. Min Range: -6.1257
Max Act: 6.1257. Min Act: -0.1700
Data Index: 8213814 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1257. Min Range: -6.1257
Max Act: 6.0632. Min Act: -0.1700
Data Index: 4089780 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1257. Min Range: -6.1257
Max Act: 5.9694. Min Act: -0.1700
Data Index: 7425990 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1257. Min Range: -6.1257
Max Act: 5.9069. Min Act: -0.1700
Data Index: 3602195 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1257. Min Range: -6.1257
Max Act: 5.8132. Min Act: -0.1700
Data Index: 6958590 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1257. Min Range: -6.1257
Max Act: 5.8444. Min Act: -0.1700
Data Index: 7130067 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1257. Min Range: -6.1257
Max Act: 5.8132. Min Act: -0.1700
Data Index: 8820935 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1257. Min Range: -6.1257
Max Act: 5.8132. Min Act: -0.1700
Data Index: 3516864 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1257. Min Range: -6.1257
Max Act: 5.8444. Min Act: -0.1700
Data Index: 7172155 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1257. Min Range: -6.1257
Max Act: 5.7819. Min Act: -0.1700
Data Index: 3504336 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1257. Min Range: -6.1257
Max Act: 5.7507. Min Act: -0.1700
Data Index: 2072448 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1257. Min Range: -6.1257
Max Act: 5.7507. Min Act: -0.1700
Data Index: 7242267 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1257. Min Range: -6.1257
Max Act: 5.7194. Min Act: -0.1700
Data Index: 4362542 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1257. Min Range: -6.1257
Max Act: 5.7194. Min Act: -0.1700
Data Index: 1966342 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1257. Min Range: -6.1257
Max Act: 5.7507. Min Act: -0.1700
Data Index: 4043534 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1257. Min Range: -6.1257
Max Act: 5.7194. Min Act: -0.1700
Data Index: 684221 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1257. Min Range: -6.1257
Max Act: 5.7194. Min Act: -0.1700
Data Index: 4490062 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1257. Min Range: -6.1257
Max Act: 5.7194. Min Act: -0.1700
Data Index: 1443616 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1257. Min Range: -6.1257
Max Act: 5.7194. Min Act: -0.1700
Data Index: 160806 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1257. Min Range: -6.1257
Max Act: 5.6882. Min Act: -0.1700
Data Index: 688103 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19