Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5100 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6988. Min Range: -5.6988
Max Act: 5.6988. Min Act: -0.1700
Data Index: 8666621 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6988. Min Range: -5.6988
Max Act: 5.6363. Min Act: -0.1700
Data Index: 1935128 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6988. Min Range: -5.6988
Max Act: 5.5425. Min Act: -0.1700
Data Index: 7156955 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6988. Min Range: -5.6988
Max Act: 5.5425. Min Act: -0.1700
Data Index: 6097165 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6988. Min Range: -5.6988
Max Act: 5.5113. Min Act: -0.1700
Data Index: 6588913 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6988. Min Range: -5.6988
Max Act: 5.5113. Min Act: -0.1699
Data Index: 4294605 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6988. Min Range: -5.6988
Max Act: 5.4800. Min Act: -0.1700
Data Index: 6562988 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6988. Min Range: -5.6988
Max Act: 5.4488. Min Act: -0.1700
Data Index: 2376546 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6988. Min Range: -5.6988
Max Act: 5.4175. Min Act: -0.1700
Data Index: 5389153 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6988. Min Range: -5.6988
Max Act: 5.4175. Min Act: -0.1700
Data Index: 5363276 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6988. Min Range: -5.6988
Max Act: 5.4488. Min Act: -0.1700
Data Index: 7824117 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6988. Min Range: -5.6988
Max Act: 5.3863. Min Act: -0.1700
Data Index: 4972800 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6988. Min Range: -5.6988
Max Act: 5.3863. Min Act: -0.1700
Data Index: 3773518 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6988. Min Range: -5.6988
Max Act: 5.3863. Min Act: -0.1700
Data Index: 8699853 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6988. Min Range: -5.6988
Max Act: 5.4175. Min Act: -0.1700
Data Index: 6227694 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6988. Min Range: -5.6988
Max Act: 5.4175. Min Act: -0.1700
Data Index: 1749565 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6988. Min Range: -5.6988
Max Act: 5.3863. Min Act: -0.1700
Data Index: 5412306 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6988. Min Range: -5.6988
Max Act: 5.3863. Min Act: -0.1700
Data Index: 2602169 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6988. Min Range: -5.6988
Max Act: 5.3863. Min Act: -0.1700
Data Index: 1318906 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6988. Min Range: -5.6988
Max Act: 5.3863. Min Act: -0.1700
Data Index: 2900182 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19