Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7438. Min Range: -4.7438
Max Act: 4.7438. Min Act: -0.1700
Data Index: 8501712 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7438. Min Range: -4.7438
Max Act: 4.7438. Min Act: -0.1700
Data Index: 6383848 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7438. Min Range: -4.7438
Max Act: 4.6813. Min Act: -0.1700
Data Index: 2112460 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7438. Min Range: -4.7438
Max Act: 4.6188. Min Act: -0.1700
Data Index: 999653 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7438. Min Range: -4.7438
Max Act: 4.5875. Min Act: -0.1700
Data Index: 6653834 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7438. Min Range: -4.7438
Max Act: 4.4938. Min Act: -0.1700
Data Index: 2863320 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7438. Min Range: -4.7438
Max Act: 4.4938. Min Act: -0.1700
Data Index: 59901 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7438. Min Range: -4.7438
Max Act: 4.4313. Min Act: -0.1700
Data Index: 6607228 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7438. Min Range: -4.7438
Max Act: 4.4313. Min Act: -0.1700
Data Index: 214241 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7438. Min Range: -4.7438
Max Act: 4.4313. Min Act: -0.1700
Data Index: 8575425 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7438. Min Range: -4.7438
Max Act: 4.4625. Min Act: -0.1700
Data Index: 8139035 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7438. Min Range: -4.7438
Max Act: 4.4313. Min Act: -0.1700
Data Index: 7656451 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7438. Min Range: -4.7438
Max Act: 4.4000. Min Act: -0.1700
Data Index: 2680412 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7438. Min Range: -4.7438
Max Act: 4.3688. Min Act: -0.1700
Data Index: 6585475 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7438. Min Range: -4.7438
Max Act: 4.3688. Min Act: -0.1700
Data Index: 2491393 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7438. Min Range: -4.7438
Max Act: 4.3375. Min Act: -0.1700
Data Index: 5860114 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7438. Min Range: -4.7438
Max Act: 4.3375. Min Act: -0.1700
Data Index: 4109445 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7438. Min Range: -4.7438
Max Act: 4.3688. Min Act: -0.1700
Data Index: 1710780 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7438. Min Range: -4.7438
Max Act: 4.3375. Min Act: -0.1700
Data Index: 360857 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7438. Min Range: -4.7438
Max Act: 4.3375. Min Act: -0.1700
Data Index: 3012126 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19