Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2378 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5143. Min Range: -7.5143
Max Act: 7.5143. Min Act: -0.1700
Data Index: 152293 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5143. Min Range: -7.5143
Max Act: 7.4205. Min Act: -0.1700
Data Index: 3808161 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5143. Min Range: -7.5143
Max Act: 7.4205. Min Act: -0.1700
Data Index: 4713772 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5143. Min Range: -7.5143
Max Act: 7.3893. Min Act: -0.1700
Data Index: 2090810 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5143. Min Range: -7.5143
Max Act: 7.3893. Min Act: -0.1700
Data Index: 5273263 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5143. Min Range: -7.5143
Max Act: 7.3580. Min Act: -0.1700
Data Index: 687406 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5143. Min Range: -7.5143
Max Act: 7.3268. Min Act: -0.1700
Data Index: 5083005 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5143. Min Range: -7.5143
Max Act: 7.3268. Min Act: -0.1700
Data Index: 1216971 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5143. Min Range: -7.5143
Max Act: 7.2955. Min Act: -0.1700
Data Index: 6900767 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5143. Min Range: -7.5143
Max Act: 7.2643. Min Act: -0.1700
Data Index: 7535450 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5143. Min Range: -7.5143
Max Act: 7.2643. Min Act: -0.1700
Data Index: 669610 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5143. Min Range: -7.5143
Max Act: 7.2018. Min Act: -0.1700
Data Index: 5537581 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5143. Min Range: -7.5143
Max Act: 7.2018. Min Act: -0.1700
Data Index: 2421466 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5143. Min Range: -7.5143
Max Act: 7.1705. Min Act: -0.1700
Data Index: 2260638 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5143. Min Range: -7.5143
Max Act: 7.1705. Min Act: -0.1700
Data Index: 2135970 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5143. Min Range: -7.5143
Max Act: 7.1705. Min Act: -0.1700
Data Index: 7983251 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5143. Min Range: -7.5143
Max Act: 7.1705. Min Act: -0.1700
Data Index: 1216970 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5143. Min Range: -7.5143
Max Act: 7.1705. Min Act: -0.1700
Data Index: 2260639 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5143. Min Range: -7.5143
Max Act: 7.1393. Min Act: -0.1700
Data Index: 4273777 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5143. Min Range: -7.5143
Max Act: 7.1393. Min Act: -0.1700
Data Index: 2135972 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19