Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4551 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5825. Min Act: -0.1700
Data Index: 3451785 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5512. Min Act: -0.1700
Data Index: 1918433 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5512. Min Act: -0.1700
Data Index: 3007720 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5825. Min Act: -0.1700
Data Index: 1569655 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5512. Min Act: -0.1700
Data Index: 7375292 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5825. Min Act: -0.1700
Data Index: 6590090 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5825. Min Act: -0.1700
Data Index: 5977321 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5512. Min Act: -0.1700
Data Index: 1231175 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5512. Min Act: -0.1700
Data Index: 1500530 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5512. Min Act: -0.1700
Data Index: 2472724 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5199. Min Act: -0.1700
Data Index: 1036675 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.4887. Min Act: -0.1700
Data Index: 7389889 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.4887. Min Act: -0.1699
Data Index: 3349447 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.4574. Min Act: -0.1700
Data Index: 1033741 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.4574. Min Act: -0.1700
Data Index: 2913661 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.4574. Min Act: -0.1698
Data Index: 7406391 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.4574. Min Act: -0.1700
Data Index: 4809331 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.4574. Min Act: -0.1700
Data Index: 7543523 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.4574. Min Act: -0.1700
Data Index: 4134318 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.4574. Min Act: -0.1700
Data Index: 7891148 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19