Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3666 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7520. Min Range: -8.7520
Max Act: 8.7520. Min Act: -0.1700
Data Index: 7325595 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7520. Min Range: -8.7520
Max Act: 8.6895. Min Act: -0.1700
Data Index: 4228629 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7520. Min Range: -8.7520
Max Act: 8.7520. Min Act: -0.1700
Data Index: 6839882 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7520. Min Range: -8.7520
Max Act: 8.6895. Min Act: -0.1700
Data Index: 4228628 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7520. Min Range: -8.7520
Max Act: 8.5645. Min Act: -0.1700
Data Index: 7325593 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7520. Min Range: -8.7520
Max Act: 8.3770. Min Act: -0.1700
Data Index: 8045517 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7520. Min Range: -8.7520
Max Act: 8.3770. Min Act: -0.1700
Data Index: 5442497 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7520. Min Range: -8.7520
Max Act: 8.3770. Min Act: -0.1700
Data Index: 6353702 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7520. Min Range: -8.7520
Max Act: 8.2520. Min Act: -0.1700
Data Index: 8824266 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7520. Min Range: -8.7520
Max Act: 8.3145. Min Act: -0.1700
Data Index: 249336 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7520. Min Range: -8.7520
Max Act: 8.1895. Min Act: -0.1700
Data Index: 3011099 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7520. Min Range: -8.7520
Max Act: 8.1895. Min Act: -0.1700
Data Index: 6827133 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7520. Min Range: -8.7520
Max Act: 8.1895. Min Act: -0.1700
Data Index: 2324882 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7520. Min Range: -8.7520
Max Act: 8.1270. Min Act: -0.1700
Data Index: 250107 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7520. Min Range: -8.7520
Max Act: 8.1582. Min Act: -0.1700
Data Index: 3911061 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7520. Min Range: -8.7520
Max Act: 8.1270. Min Act: -0.1700
Data Index: 6510205 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7520. Min Range: -8.7520
Max Act: 8.0957. Min Act: -0.1700
Data Index: 2398716 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7520. Min Range: -8.7520
Max Act: 8.0332. Min Act: -0.1700
Data Index: 6903442 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7520. Min Range: -8.7520
Max Act: 8.0645. Min Act: -0.1700
Data Index: 6060238 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7520. Min Range: -8.7520
Max Act: 7.9707. Min Act: -0.1700
Data Index: 1496198 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19