Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1597 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2810. Min Range: -3.2810
Max Act: 3.2810. Min Act: -0.1700
Data Index: 6364182 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2810. Min Range: -3.2810
Max Act: 3.2495. Min Act: -0.1700
Data Index: 5779790 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2810. Min Range: -3.2810
Max Act: 3.2181. Min Act: -0.1700
Data Index: 4139516 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2810. Min Range: -3.2810
Max Act: 3.1867. Min Act: -0.1700
Data Index: 5520345 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2810. Min Range: -3.2810
Max Act: 3.1867. Min Act: -0.1700
Data Index: 8806315 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2810. Min Range: -3.2810
Max Act: 3.2181. Min Act: -0.1700
Data Index: 4686150 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2810. Min Range: -3.2810
Max Act: 3.2181. Min Act: -0.1700
Data Index: 3919664 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2810. Min Range: -3.2810
Max Act: 3.1867. Min Act: -0.1700
Data Index: 666421 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2810. Min Range: -3.2810
Max Act: 3.1867. Min Act: -0.1700
Data Index: 7546902 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2810. Min Range: -3.2810
Max Act: 3.1867. Min Act: -0.1700
Data Index: 8505175 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2810. Min Range: -3.2810
Max Act: 3.1867. Min Act: -0.1700
Data Index: 7244973 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2810. Min Range: -3.2810
Max Act: 3.1867. Min Act: -0.1700
Data Index: 3054268 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2810. Min Range: -3.2810
Max Act: 3.1867. Min Act: -0.1700
Data Index: 3351812 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2810. Min Range: -3.2810
Max Act: 3.1552. Min Act: -0.1700
Data Index: 5288503 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2810. Min Range: -3.2810
Max Act: 3.1552. Min Act: -0.1700
Data Index: 3009373 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2810. Min Range: -3.2810
Max Act: 3.1552. Min Act: -0.1700
Data Index: 3045449 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2810. Min Range: -3.2810
Max Act: 3.1552. Min Act: -0.1700
Data Index: 1524476 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2810. Min Range: -3.2810
Max Act: 3.1552. Min Act: -0.1700
Data Index: 6256948 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2810. Min Range: -3.2810
Max Act: 3.1552. Min Act: -0.1700
Data Index: 513331 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2810. Min Range: -3.2810
Max Act: 3.1552. Min Act: -0.1700
Data Index: 6291274 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19