Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2763 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3523. Min Range: -5.3523
Max Act: 5.3523. Min Act: -0.1700
Data Index: 1814910 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3523. Min Range: -5.3523
Max Act: 5.3211. Min Act: -0.1700
Data Index: 1024829 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3523. Min Range: -5.3523
Max Act: 5.2586. Min Act: -0.1700
Data Index: 3068215 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3523. Min Range: -5.3523
Max Act: 5.1648. Min Act: -0.1700
Data Index: 1677259 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3523. Min Range: -5.3523
Max Act: 5.1023. Min Act: -0.1700
Data Index: 2539517 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3523. Min Range: -5.3523
Max Act: 5.0711. Min Act: -0.1700
Data Index: 3678957 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3523. Min Range: -5.3523
Max Act: 5.0398. Min Act: -0.1700
Data Index: 1974431 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3523. Min Range: -5.3523
Max Act: 5.0086. Min Act: -0.1700
Data Index: 8191230 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3523. Min Range: -5.3523
Max Act: 4.8523. Min Act: -0.1700
Data Index: 4752244 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3523. Min Range: -5.3523
Max Act: 4.8523. Min Act: -0.1700
Data Index: 3788616 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3523. Min Range: -5.3523
Max Act: 4.8211. Min Act: -0.1700
Data Index: 3732943 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3523. Min Range: -5.3523
Max Act: 4.7898. Min Act: -0.1700
Data Index: 3129770 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3523. Min Range: -5.3523
Max Act: 4.7898. Min Act: -0.1700
Data Index: 4544642 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3523. Min Range: -5.3523
Max Act: 4.8211. Min Act: -0.1700
Data Index: 6733432 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3523. Min Range: -5.3523
Max Act: 4.8211. Min Act: -0.1700
Data Index: 3856725 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3523. Min Range: -5.3523
Max Act: 4.8523. Min Act: -0.1700
Data Index: 8566116 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3523. Min Range: -5.3523
Max Act: 4.7898. Min Act: -0.1700
Data Index: 7988984 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3523. Min Range: -5.3523
Max Act: 4.7898. Min Act: -0.1700
Data Index: 470702 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3523. Min Range: -5.3523
Max Act: 4.7898. Min Act: -0.1700
Data Index: 7221431 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3523. Min Range: -5.3523
Max Act: 4.7898. Min Act: -0.1700
Data Index: 4525906 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19