Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4128 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4134. Min Range: -6.4134
Max Act: 6.4134. Min Act: -0.1700
Data Index: 65394 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4134. Min Range: -6.4134
Max Act: 6.0071. Min Act: -0.1700
Data Index: 487375 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4134. Min Range: -6.4134
Max Act: 5.9446. Min Act: -0.1700
Data Index: 2493678 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4134. Min Range: -6.4134
Max Act: 5.9446. Min Act: -0.1700
Data Index: 4686692 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4134. Min Range: -6.4134
Max Act: 5.9134. Min Act: -0.1700
Data Index: 4260417 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4134. Min Range: -6.4134
Max Act: 5.9134. Min Act: -0.1700
Data Index: 1142512 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4134. Min Range: -6.4134
Max Act: 5.8509. Min Act: -0.1700
Data Index: 3044295 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4134. Min Range: -6.4134
Max Act: 5.8509. Min Act: -0.1700
Data Index: 3889175 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4134. Min Range: -6.4134
Max Act: 5.8509. Min Act: -0.1700
Data Index: 2577399 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4134. Min Range: -6.4134
Max Act: 5.8196. Min Act: -0.1700
Data Index: 3263835 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4134. Min Range: -6.4134
Max Act: 5.8196. Min Act: -0.1700
Data Index: 7346690 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4134. Min Range: -6.4134
Max Act: 5.7884. Min Act: -0.1700
Data Index: 4774568 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4134. Min Range: -6.4134
Max Act: 5.7884. Min Act: -0.1700
Data Index: 6450831 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4134. Min Range: -6.4134
Max Act: 5.7571. Min Act: -0.1700
Data Index: 7369631 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4134. Min Range: -6.4134
Max Act: 5.7571. Min Act: -0.1700
Data Index: 3293739 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4134. Min Range: -6.4134
Max Act: 5.7884. Min Act: -0.1700
Data Index: 5433756 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4134. Min Range: -6.4134
Max Act: 5.7259. Min Act: -0.1700
Data Index: 7613807 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4134. Min Range: -6.4134
Max Act: 5.7571. Min Act: -0.1700
Data Index: 5514248 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4134. Min Range: -6.4134
Max Act: 5.6946. Min Act: -0.1700
Data Index: 2433237 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4134. Min Range: -6.4134
Max Act: 5.7259. Min Act: -0.1700
Data Index: 732967 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19