Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 445 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0247. Min Range: -8.0247
Max Act: 8.0247. Min Act: -0.1700
Data Index: 5253314 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0247. Min Range: -8.0247
Max Act: 7.7435. Min Act: -0.1700
Data Index: 4650882 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0247. Min Range: -8.0247
Max Act: 7.4935. Min Act: -0.1700
Data Index: 8438318 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0247. Min Range: -8.0247
Max Act: 7.4935. Min Act: -0.1700
Data Index: 879706 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0247. Min Range: -8.0247
Max Act: 7.4622. Min Act: -0.1700
Data Index: 2931142 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0247. Min Range: -8.0247
Max Act: 7.3997. Min Act: -0.1700
Data Index: 6240826 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0247. Min Range: -8.0247
Max Act: 7.4310. Min Act: -0.1700
Data Index: 7468893 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0247. Min Range: -8.0247
Max Act: 7.3685. Min Act: -0.1700
Data Index: 4680939 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0247. Min Range: -8.0247
Max Act: 7.3997. Min Act: -0.1700
Data Index: 4434971 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0247. Min Range: -8.0247
Max Act: 7.3060. Min Act: -0.1700
Data Index: 2831222 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0247. Min Range: -8.0247
Max Act: 7.2747. Min Act: -0.1700
Data Index: 1894363 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0247. Min Range: -8.0247
Max Act: 7.3060. Min Act: -0.1700
Data Index: 549821 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0247. Min Range: -8.0247
Max Act: 7.2747. Min Act: -0.1700
Data Index: 1706839 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0247. Min Range: -8.0247
Max Act: 7.2435. Min Act: -0.1700
Data Index: 8404911 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0247. Min Range: -8.0247
Max Act: 7.2435. Min Act: -0.1700
Data Index: 4294036 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0247. Min Range: -8.0247
Max Act: 7.2122. Min Act: -0.1700
Data Index: 7772645 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0247. Min Range: -8.0247
Max Act: 7.2122. Min Act: -0.1700
Data Index: 5324300 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0247. Min Range: -8.0247
Max Act: 7.1810. Min Act: -0.1700
Data Index: 1005796 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0247. Min Range: -8.0247
Max Act: 7.1497. Min Act: -0.1700
Data Index: 6622162 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0247. Min Range: -8.0247
Max Act: 7.1185. Min Act: -0.1700
Data Index: 1991054 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19