Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3268 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.1908. Min Act: -0.1700
Data Index: 6521088 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.1283. Min Act: -0.1700
Data Index: 1192776 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0971. Min Act: -0.1700
Data Index: 607657 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0971. Min Act: -0.1700
Data Index: 4569676 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0658. Min Act: -0.1700
Data Index: 5058521 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0658. Min Act: -0.1700
Data Index: 8464801 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0658. Min Act: -0.1700
Data Index: 4988015 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0658. Min Act: -0.1700
Data Index: 4416159 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0346. Min Act: -0.1700
Data Index: 6095765 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0346. Min Act: -0.1700
Data Index: 6232712 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0033. Min Act: -0.1700
Data Index: 6552389 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0033. Min Act: -0.1700
Data Index: 407291 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0033. Min Act: -0.1700
Data Index: 6467680 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0033. Min Act: -0.1700
Data Index: 4531889 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0033. Min Act: -0.1700
Data Index: 4167697 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0033. Min Act: -0.1700
Data Index: 2574823 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0033. Min Act: -0.1700
Data Index: 6250104 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0033. Min Act: -0.1700
Data Index: 3018465 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0033. Min Act: -0.1700
Data Index: 4238831 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0033. Min Act: -0.1700
Data Index: 1265139 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19