Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3622 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4553. Min Range: -5.4553
Max Act: 5.4553. Min Act: -0.1700
Data Index: 1606631 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4553. Min Range: -5.4553
Max Act: 5.4241. Min Act: -0.1700
Data Index: 2679296 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4553. Min Range: -5.4553
Max Act: 5.3928. Min Act: -0.1700
Data Index: 1606644 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4553. Min Range: -5.4553
Max Act: 5.2991. Min Act: -0.1700
Data Index: 312483 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4553. Min Range: -5.4553
Max Act: 5.2991. Min Act: -0.1700
Data Index: 3099338 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4553. Min Range: -5.4553
Max Act: 5.2366. Min Act: -0.1700
Data Index: 312481 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4553. Min Range: -5.4553
Max Act: 5.2366. Min Act: -0.1700
Data Index: 3794310 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4553. Min Range: -5.4553
Max Act: 5.2053. Min Act: -0.1700
Data Index: 3794326 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4553. Min Range: -5.4553
Max Act: 5.1741. Min Act: -0.1700
Data Index: 1443520 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4553. Min Range: -5.4553
Max Act: 5.1741. Min Act: -0.1700
Data Index: 7087514 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4553. Min Range: -5.4553
Max Act: 5.1741. Min Act: -0.1700
Data Index: 4970909 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4553. Min Range: -5.4553
Max Act: 5.2053. Min Act: -0.1700
Data Index: 1443507 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4553. Min Range: -5.4553
Max Act: 5.1428. Min Act: -0.1700
Data Index: 1589471 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4553. Min Range: -5.4553
Max Act: 5.1428. Min Act: -0.1700
Data Index: 3099356 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4553. Min Range: -5.4553
Max Act: 5.1428. Min Act: -0.1700
Data Index: 1589488 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4553. Min Range: -5.4553
Max Act: 5.1428. Min Act: -0.1700
Data Index: 4970895 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4553. Min Range: -5.4553
Max Act: 5.1116. Min Act: -0.1700
Data Index: 28522 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4553. Min Range: -5.4553
Max Act: 5.1116. Min Act: -0.1700
Data Index: 3560466 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4553. Min Range: -5.4553
Max Act: 5.1116. Min Act: -0.1700
Data Index: 2039538 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4553. Min Range: -5.4553
Max Act: 5.0803. Min Act: -0.1700
Data Index: 28535 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19