Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 440 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2900. Min Range: -5.2900
Max Act: 5.2900. Min Act: -0.1700
Data Index: 3955782 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2900. Min Range: -5.2900
Max Act: 5.1338. Min Act: -0.1700
Data Index: 1890464 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2900. Min Range: -5.2900
Max Act: 5.0713. Min Act: -0.1700
Data Index: 266385 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2900. Min Range: -5.2900
Max Act: 5.0400. Min Act: -0.1700
Data Index: 7275024 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2900. Min Range: -5.2900
Max Act: 4.9775. Min Act: -0.1700
Data Index: 2483082 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2900. Min Range: -5.2900
Max Act: 4.9463. Min Act: -0.1700
Data Index: 467554 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2900. Min Range: -5.2900
Max Act: 4.9463. Min Act: -0.1700
Data Index: 8769841 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2900. Min Range: -5.2900
Max Act: 4.9150. Min Act: -0.1700
Data Index: 5893808 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2900. Min Range: -5.2900
Max Act: 4.9463. Min Act: -0.1700
Data Index: 8022197 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2900. Min Range: -5.2900
Max Act: 4.9150. Min Act: -0.1700
Data Index: 1581178 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2900. Min Range: -5.2900
Max Act: 4.8525. Min Act: -0.1700
Data Index: 8579525 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2900. Min Range: -5.2900
Max Act: 4.8525. Min Act: -0.1700
Data Index: 8455140 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2900. Min Range: -5.2900
Max Act: 4.8525. Min Act: -0.1700
Data Index: 743648 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2900. Min Range: -5.2900
Max Act: 4.8213. Min Act: -0.1700
Data Index: 266381 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2900. Min Range: -5.2900
Max Act: 4.8213. Min Act: -0.1700
Data Index: 7243436 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2900. Min Range: -5.2900
Max Act: 4.7900. Min Act: -0.1700
Data Index: 7706642 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2900. Min Range: -5.2900
Max Act: 4.7900. Min Act: -0.1700
Data Index: 3316770 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2900. Min Range: -5.2900
Max Act: 4.7588. Min Act: -0.1700
Data Index: 3328295 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2900. Min Range: -5.2900
Max Act: 4.7588. Min Act: -0.1700
Data Index: 6269935 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2900. Min Range: -5.2900
Max Act: 4.7588. Min Act: -0.1700
Data Index: 6580448 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19