Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2816 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0986. Min Range: -6.0986
Max Act: 6.0986. Min Act: -0.1700
Data Index: 7794418 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.9423. Min Act: -0.1700
Data Index: 102143 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.8486. Min Act: -0.1700
Data Index: 7517440 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.7236. Min Act: -0.1700
Data Index: 445872 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.7236. Min Act: -0.1700
Data Index: 1346284 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.7548. Min Act: -0.1700
Data Index: 5423960 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.7236. Min Act: -0.1700
Data Index: 3451514 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.7236. Min Act: -0.1700
Data Index: 8793075 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.6298. Min Act: -0.1700
Data Index: 1618368 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.5986. Min Act: -0.1700
Data Index: 538358 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.6298. Min Act: -0.1700
Data Index: 1728473 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.5986. Min Act: -0.1700
Data Index: 385392 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.5361. Min Act: -0.1700
Data Index: 7076594 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.5673. Min Act: -0.1700
Data Index: 2703772 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.5361. Min Act: -0.1700
Data Index: 6720503 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.5361. Min Act: -0.1700
Data Index: 5150137 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.5048. Min Act: -0.1700
Data Index: 1724881 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.4736. Min Act: -0.1700
Data Index: 5851490 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.4423. Min Act: -0.1700
Data Index: 7696495 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.4111. Min Act: -0.1700
Data Index: 3103468 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19