Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1376 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0453. Min Range: -4.0453
Max Act: 4.0453. Min Act: -0.1700
Data Index: 8286323 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0453. Min Range: -4.0453
Max Act: 4.0453. Min Act: -0.1700
Data Index: 164071 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0453. Min Range: -4.0453
Max Act: 4.0453. Min Act: -0.1700
Data Index: 8162250 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0453. Min Range: -4.0453
Max Act: 4.0453. Min Act: -0.1700
Data Index: 455939 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0453. Min Range: -4.0453
Max Act: 4.0453. Min Act: -0.1700
Data Index: 8034375 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0453. Min Range: -4.0453
Max Act: 4.0140. Min Act: -0.1700
Data Index: 4710735 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0453. Min Range: -4.0453
Max Act: 4.0140. Min Act: -0.1700
Data Index: 3495808 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0453. Min Range: -4.0453
Max Act: 4.0140. Min Act: -0.1700
Data Index: 8396277 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0453. Min Range: -4.0453
Max Act: 4.0453. Min Act: -0.1700
Data Index: 2721267 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0453. Min Range: -4.0453
Max Act: 3.9828. Min Act: -0.1700
Data Index: 2824080 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0453. Min Range: -4.0453
Max Act: 3.9828. Min Act: -0.1700
Data Index: 4643092 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0453. Min Range: -4.0453
Max Act: 3.9515. Min Act: -0.1700
Data Index: 2497918 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0453. Min Range: -4.0453
Max Act: 3.9515. Min Act: -0.1700
Data Index: 5664973 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0453. Min Range: -4.0453
Max Act: 3.9515. Min Act: -0.1700
Data Index: 5926828 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0453. Min Range: -4.0453
Max Act: 3.9515. Min Act: -0.1700
Data Index: 8273539 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0453. Min Range: -4.0453
Max Act: 3.9515. Min Act: -0.1699
Data Index: 342527 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0453. Min Range: -4.0453
Max Act: 3.9515. Min Act: -0.1700
Data Index: 6193526 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0453. Min Range: -4.0453
Max Act: 3.9202. Min Act: -0.1700
Data Index: 5904868 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0453. Min Range: -4.0453
Max Act: 3.9515. Min Act: -0.1700
Data Index: 6973131 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0453. Min Range: -4.0453
Max Act: 3.9202. Min Act: -0.1700
Data Index: 5706191 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19