Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2423 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6061. Min Range: -8.6061
Max Act: 8.6061. Min Act: -0.1700
Data Index: 5919727 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6061. Min Range: -8.6061
Max Act: 8.5436. Min Act: -0.1700
Data Index: 2685545 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6061. Min Range: -8.6061
Max Act: 8.4186. Min Act: -0.1700
Data Index: 8361195 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6061. Min Range: -8.6061
Max Act: 8.3561. Min Act: -0.1700
Data Index: 8427315 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6061. Min Range: -8.6061
Max Act: 8.2936. Min Act: -0.1700
Data Index: 2133770 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6061. Min Range: -8.6061
Max Act: 8.2311. Min Act: -0.1700
Data Index: 1013515 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6061. Min Range: -8.6061
Max Act: 8.2936. Min Act: -0.1700
Data Index: 4858665 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6061. Min Range: -8.6061
Max Act: 8.2311. Min Act: -0.1700
Data Index: 2442945 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6061. Min Range: -8.6061
Max Act: 8.1686. Min Act: -0.1700
Data Index: 5233687 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6061. Min Range: -8.6061
Max Act: 8.1686. Min Act: -0.1700
Data Index: 1645328 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6061. Min Range: -8.6061
Max Act: 8.1686. Min Act: -0.1700
Data Index: 2107117 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6061. Min Range: -8.6061
Max Act: 8.1686. Min Act: -0.1700
Data Index: 125224 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6061. Min Range: -8.6061
Max Act: 8.1686. Min Act: -0.1700
Data Index: 2107116 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6061. Min Range: -8.6061
Max Act: 8.1686. Min Act: -0.1700
Data Index: 797896 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6061. Min Range: -8.6061
Max Act: 8.1061. Min Act: -0.1700
Data Index: 5010070 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6061. Min Range: -8.6061
Max Act: 8.1061. Min Act: -0.1700
Data Index: 4998075 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6061. Min Range: -8.6061
Max Act: 8.1061. Min Act: -0.1700
Data Index: 2982997 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6061. Min Range: -8.6061
Max Act: 8.0436. Min Act: -0.1700
Data Index: 1730490 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6061. Min Range: -8.6061
Max Act: 8.0436. Min Act: -0.1700
Data Index: 4741543 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6061. Min Range: -8.6061
Max Act: 8.0436. Min Act: -0.1698
Data Index: 2089234 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19