Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1279 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0574. Min Range: -4.0574
Max Act: 4.0574. Min Act: -0.1700
Data Index: 7453575 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0574. Min Range: -4.0574
Max Act: 4.0574. Min Act: -0.1700
Data Index: 4375743 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9949. Min Act: -0.1700
Data Index: 4796472 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9949. Min Act: -0.1700
Data Index: 68588 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9949. Min Act: -0.1700
Data Index: 5208234 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9636. Min Act: -0.1700
Data Index: 5337052 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9324. Min Act: -0.1700
Data Index: 2833837 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9324. Min Act: -0.1700
Data Index: 7760267 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9324. Min Act: -0.1700
Data Index: 2053523 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9324. Min Act: -0.1700
Data Index: 3911001 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9011. Min Act: -0.1700
Data Index: 672957 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9324. Min Act: -0.1700
Data Index: 8311411 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9324. Min Act: -0.1700
Data Index: 250990 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9324. Min Act: -0.1700
Data Index: 7845731 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9011. Min Act: -0.1700
Data Index: 6000036 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9011. Min Act: -0.1700
Data Index: 3077107 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9011. Min Act: -0.1700
Data Index: 4155902 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.8698. Min Act: -0.1700
Data Index: 821571 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9011. Min Act: -0.1700
Data Index: 7497837 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9011. Min Act: -0.1700
Data Index: 625826 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19