Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2940 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0046. Min Range: -4.0046
Max Act: 4.0046. Min Act: -0.1700
Data Index: 870185 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0046. Min Range: -4.0046
Max Act: 4.0046. Min Act: -0.1700
Data Index: 2459327 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0046. Min Range: -4.0046
Max Act: 4.0046. Min Act: -0.1700
Data Index: 4432833 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0046. Min Range: -4.0046
Max Act: 4.0046. Min Act: -0.1700
Data Index: 6164874 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0046. Min Range: -4.0046
Max Act: 3.9420. Min Act: -0.1700
Data Index: 7778410 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0046. Min Range: -4.0046
Max Act: 3.9420. Min Act: -0.1700
Data Index: 1791748 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0046. Min Range: -4.0046
Max Act: 3.9420. Min Act: -0.1700
Data Index: 2096937 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0046. Min Range: -4.0046
Max Act: 3.9420. Min Act: -0.1700
Data Index: 4436314 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0046. Min Range: -4.0046
Max Act: 3.9420. Min Act: -0.1700
Data Index: 6366988 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0046. Min Range: -4.0046
Max Act: 3.9733. Min Act: -0.1700
Data Index: 885180 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0046. Min Range: -4.0046
Max Act: 3.9733. Min Act: -0.1700
Data Index: 4892442 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0046. Min Range: -4.0046
Max Act: 3.9420. Min Act: -0.1700
Data Index: 1734120 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0046. Min Range: -4.0046
Max Act: 3.9420. Min Act: -0.1700
Data Index: 831014 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0046. Min Range: -4.0046
Max Act: 3.9420. Min Act: -0.1700
Data Index: 5403968 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0046. Min Range: -4.0046
Max Act: 3.9108. Min Act: -0.1700
Data Index: 5448844 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0046. Min Range: -4.0046
Max Act: 3.9108. Min Act: -0.1700
Data Index: 4892440 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0046. Min Range: -4.0046
Max Act: 3.9108. Min Act: -0.1700
Data Index: 7675795 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0046. Min Range: -4.0046
Max Act: 3.9108. Min Act: -0.1700
Data Index: 1665680 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0046. Min Range: -4.0046
Max Act: 3.9108. Min Act: -0.1700
Data Index: 2635266 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0046. Min Range: -4.0046
Max Act: 3.9108. Min Act: -0.1700
Data Index: 4892439 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19