Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2833 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4052. Min Range: -5.4052
Max Act: 5.4052. Min Act: -0.1700
Data Index: 130012 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4052. Min Range: -5.4052
Max Act: 5.3427. Min Act: -0.1700
Data Index: 1550245 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4052. Min Range: -5.4052
Max Act: 5.2802. Min Act: -0.1700
Data Index: 2569960 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4052. Min Range: -5.4052
Max Act: 5.2489. Min Act: -0.1700
Data Index: 4258978 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4052. Min Range: -5.4052
Max Act: 5.1864. Min Act: -0.1700
Data Index: 2552465 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4052. Min Range: -5.4052
Max Act: 5.1552. Min Act: -0.1700
Data Index: 3281931 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4052. Min Range: -5.4052
Max Act: 5.1552. Min Act: -0.1700
Data Index: 6301705 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4052. Min Range: -5.4052
Max Act: 5.1552. Min Act: -0.1700
Data Index: 4676494 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4052. Min Range: -5.4052
Max Act: 5.1552. Min Act: -0.1700
Data Index: 7761244 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4052. Min Range: -5.4052
Max Act: 5.1239. Min Act: -0.1700
Data Index: 8140771 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4052. Min Range: -5.4052
Max Act: 5.0927. Min Act: -0.1700
Data Index: 5755526 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4052. Min Range: -5.4052
Max Act: 5.0927. Min Act: -0.1700
Data Index: 2010760 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4052. Min Range: -5.4052
Max Act: 5.1239. Min Act: -0.1700
Data Index: 1510838 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4052. Min Range: -5.4052
Max Act: 5.1239. Min Act: -0.1700
Data Index: 222470 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4052. Min Range: -5.4052
Max Act: 5.0927. Min Act: -0.1700
Data Index: 6662875 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4052. Min Range: -5.4052
Max Act: 5.0614. Min Act: -0.1700
Data Index: 3546819 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4052. Min Range: -5.4052
Max Act: 5.0614. Min Act: -0.1700
Data Index: 5005231 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4052. Min Range: -5.4052
Max Act: 5.0614. Min Act: -0.1700
Data Index: 1924840 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4052. Min Range: -5.4052
Max Act: 5.0614. Min Act: -0.1700
Data Index: 278747 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4052. Min Range: -5.4052
Max Act: 5.0614. Min Act: -0.1700
Data Index: 1134778 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19