Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1144 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5391. Min Range: -6.5391
Max Act: 6.5391. Min Act: -0.1700
Data Index: 1984959 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5391. Min Range: -6.5391
Max Act: 6.3516. Min Act: -0.1700
Data Index: 5912629 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5391. Min Range: -6.5391
Max Act: 6.2578. Min Act: -0.1700
Data Index: 2620317 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5391. Min Range: -6.5391
Max Act: 6.2578. Min Act: -0.1700
Data Index: 7256871 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5391. Min Range: -6.5391
Max Act: 6.2891. Min Act: -0.1700
Data Index: 3964221 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5391. Min Range: -6.5391
Max Act: 6.2578. Min Act: -0.1700
Data Index: 6307082 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5391. Min Range: -6.5391
Max Act: 6.2266. Min Act: -0.1700
Data Index: 5159029 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5391. Min Range: -6.5391
Max Act: 6.1641. Min Act: -0.1700
Data Index: 6590271 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5391. Min Range: -6.5391
Max Act: 6.1328. Min Act: -0.1700
Data Index: 4982953 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5391. Min Range: -6.5391
Max Act: 6.1641. Min Act: -0.1700
Data Index: 8444055 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5391. Min Range: -6.5391
Max Act: 6.1328. Min Act: -0.1700
Data Index: 4672140 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5391. Min Range: -6.5391
Max Act: 6.1328. Min Act: -0.1700
Data Index: 3948141 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5391. Min Range: -6.5391
Max Act: 6.1641. Min Act: -0.1700
Data Index: 6586237 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5391. Min Range: -6.5391
Max Act: 6.1328. Min Act: -0.1700
Data Index: 4205491 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5391. Min Range: -6.5391
Max Act: 6.1328. Min Act: -0.1700
Data Index: 1501938 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5391. Min Range: -6.5391
Max Act: 6.1016. Min Act: -0.1700
Data Index: 604119 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5391. Min Range: -6.5391
Max Act: 6.1016. Min Act: -0.1700
Data Index: 2125920 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5391. Min Range: -6.5391
Max Act: 6.0703. Min Act: -0.1700
Data Index: 2236998 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5391. Min Range: -6.5391
Max Act: 6.0078. Min Act: -0.1700
Data Index: 7521703 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5391. Min Range: -6.5391
Max Act: 6.0703. Min Act: -0.1700
Data Index: 3297983 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19