Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2395 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0034. Min Range: -4.0034
Max Act: 4.0034. Min Act: -0.1700
Data Index: 646583 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0034. Min Range: -4.0034
Max Act: 3.8940. Min Act: -0.1700
Data Index: 1499701 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0034. Min Range: -4.0034
Max Act: 3.8627. Min Act: -0.1700
Data Index: 4096136 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0034. Min Range: -4.0034
Max Act: 3.7845. Min Act: -0.1700
Data Index: 4891526 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0034. Min Range: -4.0034
Max Act: 3.7220. Min Act: -0.1700
Data Index: 4082067 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0034. Min Range: -4.0034
Max Act: 3.7376. Min Act: -0.1700
Data Index: 1232871 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0034. Min Range: -4.0034
Max Act: 3.7376. Min Act: -0.1700
Data Index: 7920498 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0034. Min Range: -4.0034
Max Act: 3.7063. Min Act: -0.1700
Data Index: 5850570 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0034. Min Range: -4.0034
Max Act: 3.7063. Min Act: -0.1700
Data Index: 6023918 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0034. Min Range: -4.0034
Max Act: 3.6907. Min Act: -0.1700
Data Index: 4746146 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0034. Min Range: -4.0034
Max Act: 3.6907. Min Act: -0.1700
Data Index: 6752731 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0034. Min Range: -4.0034
Max Act: 3.7063. Min Act: -0.1700
Data Index: 7767035 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0034. Min Range: -4.0034
Max Act: 3.6750. Min Act: -0.1700
Data Index: 2002217 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0034. Min Range: -4.0034
Max Act: 3.6750. Min Act: -0.1700
Data Index: 4757986 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0034. Min Range: -4.0034
Max Act: 3.6594. Min Act: -0.1700
Data Index: 7488766 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0034. Min Range: -4.0034
Max Act: 3.6750. Min Act: -0.1700
Data Index: 1196263 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0034. Min Range: -4.0034
Max Act: 3.6750. Min Act: -0.1700
Data Index: 6720555 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0034. Min Range: -4.0034
Max Act: 3.6750. Min Act: -0.1700
Data Index: 3495107 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0034. Min Range: -4.0034
Max Act: 3.6907. Min Act: -0.1700
Data Index: 5142466 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0034. Min Range: -4.0034
Max Act: 3.6750. Min Act: -0.1700
Data Index: 3376451 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #19