Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1698 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3927. Min Range: -6.3927
Max Act: 6.3927. Min Act: -0.1700
Data Index: 3676237 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3927. Min Range: -6.3927
Max Act: 6.2677. Min Act: -0.1700
Data Index: 1122253 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3927. Min Range: -6.3927
Max Act: 6.0802. Min Act: -0.1700
Data Index: 5963055 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3927. Min Range: -6.3927
Max Act: 6.0802. Min Act: -0.1700
Data Index: 6653445 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3927. Min Range: -6.3927
Max Act: 6.0177. Min Act: -0.1700
Data Index: 638632 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3927. Min Range: -6.3927
Max Act: 6.0177. Min Act: -0.1700
Data Index: 7912746 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.9864. Min Act: -0.1700
Data Index: 3862504 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.9239. Min Act: -0.1700
Data Index: 3810465 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.9552. Min Act: -0.1700
Data Index: 5680972 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.9552. Min Act: -0.1700
Data Index: 5402424 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.9239. Min Act: -0.1700
Data Index: 5739849 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.8927. Min Act: -0.1700
Data Index: 972579 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.8927. Min Act: -0.1700
Data Index: 6987363 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.8927. Min Act: -0.1700
Data Index: 6697353 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.8302. Min Act: -0.1700
Data Index: 4943341 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.8302. Min Act: -0.1700
Data Index: 6613398 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.8302. Min Act: -0.1700
Data Index: 2029543 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.7989. Min Act: -0.1700
Data Index: 5680975 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.8302. Min Act: -0.1700
Data Index: 3575520 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.8302. Min Act: -0.1700
Data Index: 8758962 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19