Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1672 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2124. Min Range: -4.2124
Max Act: 4.2124. Min Act: -0.1700
Data Index: 7030173 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2124. Min Range: -4.2124
Max Act: 4.1499. Min Act: -0.1700
Data Index: 4937217 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2124. Min Range: -4.2124
Max Act: 4.0874. Min Act: -0.1700
Data Index: 8422749 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2124. Min Range: -4.2124
Max Act: 4.0874. Min Act: -0.1700
Data Index: 282234 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2124. Min Range: -4.2124
Max Act: 4.0561. Min Act: -0.1700
Data Index: 4619551 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2124. Min Range: -4.2124
Max Act: 4.0249. Min Act: -0.1700
Data Index: 264218 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2124. Min Range: -4.2124
Max Act: 4.0249. Min Act: -0.1700
Data Index: 6973892 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2124. Min Range: -4.2124
Max Act: 4.0249. Min Act: -0.1700
Data Index: 1538279 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.9936. Min Act: -0.1700
Data Index: 1325815 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.9936. Min Act: -0.1700
Data Index: 7149747 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.9936. Min Act: -0.1700
Data Index: 2052816 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.9623. Min Act: -0.1700
Data Index: 5345434 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.9623. Min Act: -0.1700
Data Index: 8680352 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.9311. Min Act: -0.1700
Data Index: 1027567 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.9311. Min Act: -0.1700
Data Index: 745801 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.9311. Min Act: -0.1700
Data Index: 4156000 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.8998. Min Act: -0.1700
Data Index: 7578987 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.8998. Min Act: -0.1700
Data Index: 2787744 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.8998. Min Act: -0.1700
Data Index: 2197260 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.8998. Min Act: -0.1700
Data Index: 531183 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19