Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3605 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2054. Min Range: -7.2054
Max Act: 7.2054. Min Act: -0.1700
Data Index: 1473662 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2054. Min Range: -7.2054
Max Act: 7.1429. Min Act: -0.1700
Data Index: 559103 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2054. Min Range: -7.2054
Max Act: 6.9242. Min Act: -0.1700
Data Index: 7015579 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2054. Min Range: -7.2054
Max Act: 6.8929. Min Act: -0.1700
Data Index: 3828640 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2054. Min Range: -7.2054
Max Act: 6.8617. Min Act: -0.1700
Data Index: 7418618 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2054. Min Range: -7.2054
Max Act: 6.8304. Min Act: -0.1700
Data Index: 1142439 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2054. Min Range: -7.2054
Max Act: 6.7992. Min Act: -0.1700
Data Index: 1142440 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2054. Min Range: -7.2054
Max Act: 6.6742. Min Act: -0.1700
Data Index: 4240231 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2054. Min Range: -7.2054
Max Act: 6.6742. Min Act: -0.1700
Data Index: 1260198 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2054. Min Range: -7.2054
Max Act: 6.6117. Min Act: -0.1700
Data Index: 1967321 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2054. Min Range: -7.2054
Max Act: 6.6117. Min Act: -0.1700
Data Index: 95366 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2054. Min Range: -7.2054
Max Act: 6.6117. Min Act: -0.1700
Data Index: 3617030 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2054. Min Range: -7.2054
Max Act: 6.6117. Min Act: -0.1700
Data Index: 5179728 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2054. Min Range: -7.2054
Max Act: 6.5804. Min Act: -0.1700
Data Index: 3732231 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2054. Min Range: -7.2054
Max Act: 6.5492. Min Act: -0.1700
Data Index: 4778064 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2054. Min Range: -7.2054
Max Act: 6.5179. Min Act: -0.1700
Data Index: 5508865 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2054. Min Range: -7.2054
Max Act: 6.5179. Min Act: -0.1700
Data Index: 2275866 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2054. Min Range: -7.2054
Max Act: 6.4867. Min Act: -0.1700
Data Index: 4363460 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2054. Min Range: -7.2054
Max Act: 6.4554. Min Act: -0.1700
Data Index: 4127901 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2054. Min Range: -7.2054
Max Act: 6.4867. Min Act: -0.1700
Data Index: 6407753 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19