Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3006 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9268. Min Range: -5.9268
Max Act: 5.9268. Min Act: -0.1700
Data Index: 336634 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9268. Min Range: -5.9268
Max Act: 5.5206. Min Act: -0.1700
Data Index: 3737512 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9268. Min Range: -5.9268
Max Act: 5.5206. Min Act: -0.1700
Data Index: 1599527 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9268. Min Range: -5.9268
Max Act: 5.4893. Min Act: -0.1700
Data Index: 8447254 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9268. Min Range: -5.9268
Max Act: 5.3956. Min Act: -0.1700
Data Index: 6103374 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9268. Min Range: -5.9268
Max Act: 5.3331. Min Act: -0.1700
Data Index: 6204777 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9268. Min Range: -5.9268
Max Act: 5.3018. Min Act: -0.1700
Data Index: 6498988 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9268. Min Range: -5.9268
Max Act: 5.3331. Min Act: -0.1700
Data Index: 7019054 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9268. Min Range: -5.9268
Max Act: 5.3018. Min Act: -0.1700
Data Index: 2392872 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9268. Min Range: -5.9268
Max Act: 5.3018. Min Act: -0.1700
Data Index: 2133354 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9268. Min Range: -5.9268
Max Act: 5.3018. Min Act: -0.1700
Data Index: 2376540 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9268. Min Range: -5.9268
Max Act: 5.3018. Min Act: -0.1700
Data Index: 1393101 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9268. Min Range: -5.9268
Max Act: 5.3018. Min Act: -0.1700
Data Index: 2043271 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9268. Min Range: -5.9268
Max Act: 5.3018. Min Act: -0.1700
Data Index: 706762 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9268. Min Range: -5.9268
Max Act: 5.3018. Min Act: -0.1700
Data Index: 1609231 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9268. Min Range: -5.9268
Max Act: 5.3018. Min Act: -0.1700
Data Index: 955297 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9268. Min Range: -5.9268
Max Act: 5.3018. Min Act: -0.1700
Data Index: 2195302 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9268. Min Range: -5.9268
Max Act: 5.3018. Min Act: -0.1700
Data Index: 510939 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9268. Min Range: -5.9268
Max Act: 5.3018. Min Act: -0.1700
Data Index: 1613736 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9268. Min Range: -5.9268
Max Act: 5.3018. Min Act: -0.1700
Data Index: 2264905 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19