Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4801 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0709. Min Range: -3.0709
Max Act: 3.0709. Min Act: -0.1700
Data Index: 2871508 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0709. Min Range: -3.0709
Max Act: 3.0709. Min Act: -0.1700
Data Index: 2338662 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0709. Min Range: -3.0709
Max Act: 3.0709. Min Act: -0.1700
Data Index: 4452809 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.9761. Min Act: -0.1700
Data Index: 3093948 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.9445. Min Act: -0.1700
Data Index: 8653888 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.9603. Min Act: -0.1700
Data Index: 3455798 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.9603. Min Act: -0.1700
Data Index: 2192142 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.9445. Min Act: -0.1700
Data Index: 351327 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.9445. Min Act: -0.1700
Data Index: 4626415 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.9128. Min Act: -0.1700
Data Index: 8777597 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.9286. Min Act: -0.1700
Data Index: 3510375 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.9286. Min Act: -0.1700
Data Index: 7867717 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.9128. Min Act: -0.1700
Data Index: 7637697 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.9286. Min Act: -0.1700
Data Index: 7309176 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.9286. Min Act: -0.1700
Data Index: 7252546 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.9286. Min Act: -0.1700
Data Index: 4112956 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.9286. Min Act: -0.1700
Data Index: 7140108 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.8969. Min Act: -0.1700
Data Index: 3359748 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.8969. Min Act: -0.1700
Data Index: 8002961 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.8969. Min Act: -0.1700
Data Index: 6439166 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19