Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3916 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6702. Min Range: -3.6702
Max Act: 3.6702. Min Act: -0.1700
Data Index: 270640 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6702. Min Range: -3.6702
Max Act: 3.6546. Min Act: -0.1700
Data Index: 1859731 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6702. Min Range: -3.6702
Max Act: 3.6233. Min Act: -0.1700
Data Index: 5108244 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6702. Min Range: -3.6702
Max Act: 3.6389. Min Act: -0.1700
Data Index: 2990432 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6702. Min Range: -3.6702
Max Act: 3.6077. Min Act: -0.1700
Data Index: 5854410 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6702. Min Range: -3.6702
Max Act: 3.6077. Min Act: -0.1700
Data Index: 551634 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6702. Min Range: -3.6702
Max Act: 3.6077. Min Act: -0.1700
Data Index: 7067299 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6702. Min Range: -3.6702
Max Act: 3.5920. Min Act: -0.1700
Data Index: 1393577 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6702. Min Range: -3.6702
Max Act: 3.5920. Min Act: -0.1700
Data Index: 2961756 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6702. Min Range: -3.6702
Max Act: 3.5763. Min Act: -0.1700
Data Index: 2000832 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6702. Min Range: -3.6702
Max Act: 3.5920. Min Act: -0.1700
Data Index: 4223067 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6702. Min Range: -3.6702
Max Act: 3.5763. Min Act: -0.1700
Data Index: 7237241 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6702. Min Range: -3.6702
Max Act: 3.5450. Min Act: -0.1700
Data Index: 5142055 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6702. Min Range: -3.6702
Max Act: 3.5450. Min Act: -0.1700
Data Index: 3106580 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6702. Min Range: -3.6702
Max Act: 3.5294. Min Act: -0.1700
Data Index: 2715682 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6702. Min Range: -3.6702
Max Act: 3.5294. Min Act: -0.1700
Data Index: 7291085 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6702. Min Range: -3.6702
Max Act: 3.5137. Min Act: -0.1700
Data Index: 5724278 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6702. Min Range: -3.6702
Max Act: 3.5137. Min Act: -0.1700
Data Index: 1276504 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6702. Min Range: -3.6702
Max Act: 3.5137. Min Act: -0.1700
Data Index: 5027543 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6702. Min Range: -3.6702
Max Act: 3.5137. Min Act: -0.1700
Data Index: 854483 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19