Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3673 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1520. Min Range: -5.1520
Max Act: 5.1520. Min Act: -0.1700
Data Index: 2516432 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1520. Min Range: -5.1520
Max Act: 5.0895. Min Act: -0.1700
Data Index: 443420 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1520. Min Range: -5.1520
Max Act: 5.0270. Min Act: -0.1700
Data Index: 2865380 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1520. Min Range: -5.1520
Max Act: 4.9332. Min Act: -0.1700
Data Index: 1162725 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1520. Min Range: -5.1520
Max Act: 4.9332. Min Act: -0.1700
Data Index: 2072712 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1520. Min Range: -5.1520
Max Act: 4.8707. Min Act: -0.1700
Data Index: 3529562 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1520. Min Range: -5.1520
Max Act: 4.8395. Min Act: -0.1700
Data Index: 5415118 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1520. Min Range: -5.1520
Max Act: 4.8395. Min Act: -0.1700
Data Index: 5513992 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1520. Min Range: -5.1520
Max Act: 4.8395. Min Act: -0.1700
Data Index: 2205053 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1520. Min Range: -5.1520
Max Act: 4.7770. Min Act: -0.1700
Data Index: 8508500 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1520. Min Range: -5.1520
Max Act: 4.7457. Min Act: -0.1700
Data Index: 1783754 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1520. Min Range: -5.1520
Max Act: 4.7145. Min Act: -0.1700
Data Index: 962480 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1520. Min Range: -5.1520
Max Act: 4.7457. Min Act: -0.1700
Data Index: 5234682 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1520. Min Range: -5.1520
Max Act: 4.7145. Min Act: -0.1700
Data Index: 4713181 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1520. Min Range: -5.1520
Max Act: 4.6832. Min Act: -0.1700
Data Index: 3642206 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1520. Min Range: -5.1520
Max Act: 4.6832. Min Act: -0.1700
Data Index: 2603118 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1520. Min Range: -5.1520
Max Act: 4.6832. Min Act: -0.1700
Data Index: 3101822 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1520. Min Range: -5.1520
Max Act: 4.6832. Min Act: -0.1700
Data Index: 265528 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1520. Min Range: -5.1520
Max Act: 4.6520. Min Act: -0.1700
Data Index: 955522 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1520. Min Range: -5.1520
Max Act: 4.6520. Min Act: -0.1700
Data Index: 123750 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19