Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4463. Min Range: -7.4463
Max Act: 7.4463. Min Act: -0.1700
Data Index: 2378121 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4463. Min Range: -7.4463
Max Act: 7.3526. Min Act: -0.1700
Data Index: 240213 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4463. Min Range: -7.4463
Max Act: 7.2901. Min Act: -0.1700
Data Index: 198428 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4463. Min Range: -7.4463
Max Act: 7.1651. Min Act: -0.1700
Data Index: 2396094 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4463. Min Range: -7.4463
Max Act: 7.1338. Min Act: -0.1700
Data Index: 1207018 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4463. Min Range: -7.4463
Max Act: 7.0713. Min Act: -0.1700
Data Index: 1620797 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4463. Min Range: -7.4463
Max Act: 7.1026. Min Act: -0.1699
Data Index: 8664191 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4463. Min Range: -7.4463
Max Act: 7.0713. Min Act: -0.1700
Data Index: 8177052 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4463. Min Range: -7.4463
Max Act: 7.0713. Min Act: -0.1700
Data Index: 7282613 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4463. Min Range: -7.4463
Max Act: 7.0088. Min Act: -0.1700
Data Index: 7114700 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4463. Min Range: -7.4463
Max Act: 6.9776. Min Act: -0.1700
Data Index: 5275652 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4463. Min Range: -7.4463
Max Act: 7.0088. Min Act: -0.1700
Data Index: 6077335 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4463. Min Range: -7.4463
Max Act: 6.9776. Min Act: -0.1700
Data Index: 7530025 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4463. Min Range: -7.4463
Max Act: 7.0088. Min Act: -0.1700
Data Index: 229676 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4463. Min Range: -7.4463
Max Act: 6.9776. Min Act: -0.1700
Data Index: 6469595 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4463. Min Range: -7.4463
Max Act: 6.9776. Min Act: -0.1700
Data Index: 6656740 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4463. Min Range: -7.4463
Max Act: 6.9776. Min Act: -0.1700
Data Index: 4201446 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4463. Min Range: -7.4463
Max Act: 6.9151. Min Act: -0.1700
Data Index: 8252645 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4463. Min Range: -7.4463
Max Act: 6.9463. Min Act: -0.1700
Data Index: 1865368 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4463. Min Range: -7.4463
Max Act: 6.9463. Min Act: -0.1700
Data Index: 3263645 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19