Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4114 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9220. Min Range: -5.9220
Max Act: 5.9220. Min Act: -0.1700
Data Index: 3739239 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9220. Min Range: -5.9220
Max Act: 5.8907. Min Act: -0.1700
Data Index: 6486492 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9220. Min Range: -5.9220
Max Act: 5.8907. Min Act: -0.1700
Data Index: 874855 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9220. Min Range: -5.9220
Max Act: 5.8282. Min Act: -0.1700
Data Index: 6209778 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9220. Min Range: -5.9220
Max Act: 5.8282. Min Act: -0.1700
Data Index: 4941470 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9220. Min Range: -5.9220
Max Act: 5.7970. Min Act: -0.1700
Data Index: 6340953 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9220. Min Range: -5.9220
Max Act: 5.7657. Min Act: -0.1700
Data Index: 1715964 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9220. Min Range: -5.9220
Max Act: 5.7657. Min Act: -0.1700
Data Index: 2165052 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9220. Min Range: -5.9220
Max Act: 5.7345. Min Act: -0.1700
Data Index: 5060377 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9220. Min Range: -5.9220
Max Act: 5.7345. Min Act: -0.1700
Data Index: 6076018 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9220. Min Range: -5.9220
Max Act: 5.7345. Min Act: -0.1700
Data Index: 1661114 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9220. Min Range: -5.9220
Max Act: 5.7345. Min Act: -0.1700
Data Index: 4757295 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9220. Min Range: -5.9220
Max Act: 5.7345. Min Act: -0.1700
Data Index: 171465 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9220. Min Range: -5.9220
Max Act: 5.7032. Min Act: -0.1700
Data Index: 240389 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9220. Min Range: -5.9220
Max Act: 5.7032. Min Act: -0.1700
Data Index: 7606426 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9220. Min Range: -5.9220
Max Act: 5.7032. Min Act: -0.1700
Data Index: 2654681 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9220. Min Range: -5.9220
Max Act: 5.7032. Min Act: -0.1700
Data Index: 7914502 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9220. Min Range: -5.9220
Max Act: 5.6407. Min Act: -0.1700
Data Index: 8251983 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9220. Min Range: -5.9220
Max Act: 5.6720. Min Act: -0.1700
Data Index: 4239297 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9220. Min Range: -5.9220
Max Act: 5.6407. Min Act: -0.1700
Data Index: 3351900 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19