Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3824 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.1451. Min Range: -1.1451
Max Act: 1.1451. Min Act: -0.1700
Data Index: 5209351 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1451. Min Range: -1.1451
Max Act: 1.1100. Min Act: -0.1700
Data Index: 3647704 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1451. Min Range: -1.1451
Max Act: 1.0575. Min Act: -0.1700
Data Index: 6123123 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1451. Min Range: -1.1451
Max Act: 1.0749. Min Act: -0.1700
Data Index: 7753989 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1451. Min Range: -1.1451
Max Act: 1.0052. Min Act: -0.1700
Data Index: 2589983 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1451. Min Range: -1.1451
Max Act: 1.0052. Min Act: -0.1700
Data Index: 7278026 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1451. Min Range: -1.1451
Max Act: 1.0052. Min Act: -0.1700
Data Index: 3599102 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1451. Min Range: -1.1451
Max Act: 1.0052. Min Act: -0.1700
Data Index: 2147641 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1451. Min Range: -1.1451
Max Act: 1.0052. Min Act: -0.1700
Data Index: 419631 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1451. Min Range: -1.1451
Max Act: 0.9879. Min Act: -0.1700
Data Index: 3508584 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1451. Min Range: -1.1451
Max Act: 0.9533. Min Act: -0.1700
Data Index: 2919546 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1451. Min Range: -1.1451
Max Act: 0.9706. Min Act: -0.1700
Data Index: 1823843 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1451. Min Range: -1.1451
Max Act: 0.9533. Min Act: -0.1700
Data Index: 8785255 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1451. Min Range: -1.1451
Max Act: 0.9533. Min Act: -0.1700
Data Index: 6420928 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1451. Min Range: -1.1451
Max Act: 0.9533. Min Act: -0.1700
Data Index: 1196396 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1451. Min Range: -1.1451
Max Act: 0.9533. Min Act: -0.1700
Data Index: 8827307 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1451. Min Range: -1.1451
Max Act: 0.9533. Min Act: -0.1700
Data Index: 7522954 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1451. Min Range: -1.1451
Max Act: 0.9275. Min Act: -0.1700
Data Index: 3286485 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1451. Min Range: -1.1451
Max Act: 0.9361. Min Act: -0.1700
Data Index: 1758641 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1451. Min Range: -1.1451
Max Act: 0.9361. Min Act: -0.1700
Data Index: 2262028 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19