Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2385 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5836. Min Range: -4.5836
Max Act: 4.5836. Min Act: -0.1700
Data Index: 1980462 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5836. Min Range: -4.5836
Max Act: 4.5836. Min Act: -0.1700
Data Index: 1219868 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5836. Min Range: -4.5836
Max Act: 4.5523. Min Act: -0.1700
Data Index: 6529369 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5836. Min Range: -4.5836
Max Act: 4.5523. Min Act: -0.1700
Data Index: 202370 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5836. Min Range: -4.5836
Max Act: 4.5523. Min Act: -0.1700
Data Index: 4846655 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5836. Min Range: -4.5836
Max Act: 4.5523. Min Act: -0.1700
Data Index: 5094461 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5836. Min Range: -4.5836
Max Act: 4.5523. Min Act: -0.1700
Data Index: 3179499 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5836. Min Range: -4.5836
Max Act: 4.5523. Min Act: -0.1700
Data Index: 8190571 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5836. Min Range: -4.5836
Max Act: 4.5523. Min Act: -0.1700
Data Index: 1428749 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5836. Min Range: -4.5836
Max Act: 4.5523. Min Act: -0.1700
Data Index: 5574161 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5836. Min Range: -4.5836
Max Act: 4.5523. Min Act: -0.1700
Data Index: 3931638 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5836. Min Range: -4.5836
Max Act: 4.5211. Min Act: -0.1700
Data Index: 3735954 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5836. Min Range: -4.5836
Max Act: 4.5211. Min Act: -0.1700
Data Index: 4597270 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5836. Min Range: -4.5836
Max Act: 4.5211. Min Act: -0.1700
Data Index: 4357293 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5836. Min Range: -4.5836
Max Act: 4.5211. Min Act: -0.1700
Data Index: 1765407 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5836. Min Range: -4.5836
Max Act: 4.5211. Min Act: -0.1700
Data Index: 3982918 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5836. Min Range: -4.5836
Max Act: 4.5211. Min Act: -0.1700
Data Index: 1376378 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5836. Min Range: -4.5836
Max Act: 4.5211. Min Act: -0.1700
Data Index: 4805304 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5836. Min Range: -4.5836
Max Act: 4.5211. Min Act: -0.1700
Data Index: 522711 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5836. Min Range: -4.5836
Max Act: 4.5211. Min Act: -0.1700
Data Index: 841753 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19