Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4520 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3462. Min Range: -6.3462
Max Act: 6.3462. Min Act: -0.1700
Data Index: 41439 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3462. Min Range: -6.3462
Max Act: 6.1275. Min Act: -0.1700
Data Index: 1552696 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3462. Min Range: -6.3462
Max Act: 6.0962. Min Act: -0.1700
Data Index: 4226395 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3462. Min Range: -6.3462
Max Act: 6.0962. Min Act: -0.1700
Data Index: 1757092 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3462. Min Range: -6.3462
Max Act: 6.0650. Min Act: -0.1700
Data Index: 2955667 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3462. Min Range: -6.3462
Max Act: 6.0025. Min Act: -0.1700
Data Index: 4195366 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3462. Min Range: -6.3462
Max Act: 6.0025. Min Act: -0.1700
Data Index: 5093946 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3462. Min Range: -6.3462
Max Act: 6.0025. Min Act: -0.1700
Data Index: 769184 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3462. Min Range: -6.3462
Max Act: 5.9400. Min Act: -0.1700
Data Index: 7248217 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3462. Min Range: -6.3462
Max Act: 6.0025. Min Act: -0.1700
Data Index: 2292495 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3462. Min Range: -6.3462
Max Act: 5.9712. Min Act: -0.1700
Data Index: 2350837 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3462. Min Range: -6.3462
Max Act: 5.9400. Min Act: -0.1700
Data Index: 2596445 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3462. Min Range: -6.3462
Max Act: 5.9400. Min Act: -0.1700
Data Index: 3851491 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3462. Min Range: -6.3462
Max Act: 5.9087. Min Act: -0.1700
Data Index: 1621000 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3462. Min Range: -6.3462
Max Act: 5.8775. Min Act: -0.1700
Data Index: 8455959 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3462. Min Range: -6.3462
Max Act: 5.9087. Min Act: -0.1700
Data Index: 5088830 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3462. Min Range: -6.3462
Max Act: 5.8775. Min Act: -0.1700
Data Index: 3532545 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3462. Min Range: -6.3462
Max Act: 5.9087. Min Act: -0.1700
Data Index: 7442720 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3462. Min Range: -6.3462
Max Act: 5.8462. Min Act: -0.1700
Data Index: 3829248 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3462. Min Range: -6.3462
Max Act: 5.8775. Min Act: -0.1700
Data Index: 8567298 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19