Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3280 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.4144. Min Act: -0.1700
Data Index: 4354836 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.3519. Min Act: -0.1700
Data Index: 3870413 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.2894. Min Act: -0.1700
Data Index: 8799564 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.2894. Min Act: -0.1700
Data Index: 6986165 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.2582. Min Act: -0.1700
Data Index: 8526203 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.2894. Min Act: -0.1700
Data Index: 4971384 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.2894. Min Act: -0.1700
Data Index: 4996290 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.2269. Min Act: -0.1700
Data Index: 847266 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.2269. Min Act: -0.1700
Data Index: 3078998 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.1644. Min Act: -0.1700
Data Index: 4688010 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.1332. Min Act: -0.1700
Data Index: 618842 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.1332. Min Act: -0.1700
Data Index: 8799563 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.1332. Min Act: -0.1700
Data Index: 2246622 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.1332. Min Act: -0.1700
Data Index: 2224233 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.1019. Min Act: -0.1700
Data Index: 3956387 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.1019. Min Act: -0.1700
Data Index: 42996 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.1019. Min Act: -0.1700
Data Index: 6354924 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.0707. Min Act: -0.1700
Data Index: 7686266 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.0707. Min Act: -0.1700
Data Index: 3835390 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.0707. Min Act: -0.1700
Data Index: 7295646 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19