Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 914 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5662. Min Range: -4.5662
Max Act: 4.5662. Min Act: -0.1700
Data Index: 4747690 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5662. Min Range: -4.5662
Max Act: 4.5662. Min Act: -0.1700
Data Index: 3833813 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5662. Min Range: -4.5662
Max Act: 4.5350. Min Act: -0.1700
Data Index: 7088646 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5662. Min Range: -4.5662
Max Act: 4.5350. Min Act: -0.1700
Data Index: 7425141 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5662. Min Range: -4.5662
Max Act: 4.5350. Min Act: -0.1693
Data Index: 8071853 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5662. Min Range: -4.5662
Max Act: 4.5350. Min Act: -0.1700
Data Index: 2143767 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5662. Min Range: -4.5662
Max Act: 4.5037. Min Act: -0.1700
Data Index: 2240342 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5662. Min Range: -4.5662
Max Act: 4.4725. Min Act: -0.1700
Data Index: 1739072 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5662. Min Range: -4.5662
Max Act: 4.5037. Min Act: -0.1700
Data Index: 4065937 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5662. Min Range: -4.5662
Max Act: 4.5037. Min Act: -0.1700
Data Index: 5567990 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5662. Min Range: -4.5662
Max Act: 4.5037. Min Act: -0.1699
Data Index: 1045655 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5662. Min Range: -4.5662
Max Act: 4.5037. Min Act: -0.1700
Data Index: 1025696 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5662. Min Range: -4.5662
Max Act: 4.4725. Min Act: -0.1700
Data Index: 7646290 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5662. Min Range: -4.5662
Max Act: 4.4725. Min Act: -0.1700
Data Index: 7474381 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5662. Min Range: -4.5662
Max Act: 4.4725. Min Act: -0.1700
Data Index: 5595508 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5662. Min Range: -4.5662
Max Act: 4.4725. Min Act: -0.1700
Data Index: 5138305 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5662. Min Range: -4.5662
Max Act: 4.4412. Min Act: -0.1700
Data Index: 1862877 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5662. Min Range: -4.5662
Max Act: 4.4412. Min Act: -0.1700
Data Index: 5634766 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5662. Min Range: -4.5662
Max Act: 4.4412. Min Act: -0.1700
Data Index: 6153230 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5662. Min Range: -4.5662
Max Act: 4.4412. Min Act: -0.1700
Data Index: 6607364 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19