Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2565 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.7307. Min Range: -0.7307
Max Act: 0.7307. Min Act: -0.1700
Data Index: 2034453 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7307. Min Range: -0.7307
Max Act: 0.7224. Min Act: -0.1700
Data Index: 4777350 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7307. Min Range: -0.7307
Max Act: 0.6654. Min Act: -0.1698
Data Index: 8294038 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7307. Min Range: -0.7307
Max Act: 0.6413. Min Act: -0.1700
Data Index: 8738199 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7307. Min Range: -0.7307
Max Act: 0.6254. Min Act: -0.1699
Data Index: 7977240 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7307. Min Range: -0.7307
Max Act: 0.6254. Min Act: -0.1700
Data Index: 5192283 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7307. Min Range: -0.7307
Max Act: 0.6175. Min Act: -0.1700
Data Index: 4388910 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7307. Min Range: -0.7307
Max Act: 0.6175. Min Act: -0.1700
Data Index: 5879481 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7307. Min Range: -0.7307
Max Act: 0.6175. Min Act: -0.1700
Data Index: 5996720 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7307. Min Range: -0.7307
Max Act: 0.6175. Min Act: -0.1700
Data Index: 6726775 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7307. Min Range: -0.7307
Max Act: 0.6254. Min Act: -0.1698
Data Index: 7497629 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7307. Min Range: -0.7307
Max Act: 0.6095. Min Act: -0.1698
Data Index: 8434833 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7307. Min Range: -0.7307
Max Act: 0.5938. Min Act: -0.1700
Data Index: 4846417 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7307. Min Range: -0.7307
Max Act: 0.6017. Min Act: -0.1700
Data Index: 3988471 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7307. Min Range: -0.7307
Max Act: 0.5938. Min Act: -0.1697
Data Index: 876402 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7307. Min Range: -0.7307
Max Act: 0.6017. Min Act: -0.1692
Data Index: 8367086 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7307. Min Range: -0.7307
Max Act: 0.5938. Min Act: -0.1700
Data Index: 3772067 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7307. Min Range: -0.7307
Max Act: 0.5860. Min Act: -0.1694
Data Index: 782628 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7307. Min Range: -0.7307
Max Act: 0.5938. Min Act: -0.1700
Data Index: 2245909 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7307. Min Range: -0.7307
Max Act: 0.6095. Min Act: -0.1700
Data Index: 7131499 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19