Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5984 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1370. Min Range: -5.1370
Max Act: 5.1370. Min Act: -0.1700
Data Index: 7030098 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1370. Min Range: -5.1370
Max Act: 5.0433. Min Act: -0.1700
Data Index: 3499827 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1370. Min Range: -5.1370
Max Act: 5.0433. Min Act: -0.1700
Data Index: 7068319 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1370. Min Range: -5.1370
Max Act: 5.0120. Min Act: -0.1700
Data Index: 4894202 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1370. Min Range: -5.1370
Max Act: 4.9495. Min Act: -0.1700
Data Index: 7083820 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1370. Min Range: -5.1370
Max Act: 4.9183. Min Act: -0.1700
Data Index: 3931154 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1370. Min Range: -5.1370
Max Act: 4.8245. Min Act: -0.1700
Data Index: 2483147 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1370. Min Range: -5.1370
Max Act: 4.7620. Min Act: -0.1700
Data Index: 79424 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1370. Min Range: -5.1370
Max Act: 4.7620. Min Act: -0.1700
Data Index: 4420655 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1370. Min Range: -5.1370
Max Act: 4.7620. Min Act: -0.1700
Data Index: 344592 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1370. Min Range: -5.1370
Max Act: 4.7308. Min Act: -0.1700
Data Index: 259578 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1370. Min Range: -5.1370
Max Act: 4.7620. Min Act: -0.1700
Data Index: 8652009 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1370. Min Range: -5.1370
Max Act: 4.7308. Min Act: -0.1700
Data Index: 8239536 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1370. Min Range: -5.1370
Max Act: 4.6995. Min Act: -0.1699
Data Index: 703273 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1370. Min Range: -5.1370
Max Act: 4.6995. Min Act: -0.1700
Data Index: 6717214 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1370. Min Range: -5.1370
Max Act: 4.6995. Min Act: -0.1700
Data Index: 4466419 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1370. Min Range: -5.1370
Max Act: 4.6370. Min Act: -0.1700
Data Index: 2977620 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1370. Min Range: -5.1370
Max Act: 4.6683. Min Act: -0.1700
Data Index: 4378222 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1370. Min Range: -5.1370
Max Act: 4.6683. Min Act: -0.1700
Data Index: 3225376 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1370. Min Range: -5.1370
Max Act: 4.6683. Min Act: -0.1700
Data Index: 900900 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19