Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1741 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3710. Min Range: -6.3710
Max Act: 6.3710. Min Act: -0.1700
Data Index: 898047 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3710. Min Range: -6.3710
Max Act: 6.3397. Min Act: -0.1700
Data Index: 2469912 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3710. Min Range: -6.3710
Max Act: 6.1522. Min Act: -0.1700
Data Index: 8019792 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3710. Min Range: -6.3710
Max Act: 6.1522. Min Act: -0.1700
Data Index: 5658969 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3710. Min Range: -6.3710
Max Act: 6.0897. Min Act: -0.1700
Data Index: 3845186 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3710. Min Range: -6.3710
Max Act: 6.0272. Min Act: -0.1700
Data Index: 5270135 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3710. Min Range: -6.3710
Max Act: 6.0272. Min Act: -0.1700
Data Index: 7788096 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3710. Min Range: -6.3710
Max Act: 6.0272. Min Act: -0.1700
Data Index: 4857312 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3710. Min Range: -6.3710
Max Act: 5.9960. Min Act: -0.1700
Data Index: 585993 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3710. Min Range: -6.3710
Max Act: 5.9647. Min Act: -0.1700
Data Index: 2017501 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3710. Min Range: -6.3710
Max Act: 5.9960. Min Act: -0.1700
Data Index: 173605 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3710. Min Range: -6.3710
Max Act: 5.9960. Min Act: -0.1700
Data Index: 2492939 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3710. Min Range: -6.3710
Max Act: 5.9647. Min Act: -0.1700
Data Index: 7610452 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3710. Min Range: -6.3710
Max Act: 5.9647. Min Act: -0.1700
Data Index: 7740271 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3710. Min Range: -6.3710
Max Act: 5.9647. Min Act: -0.1700
Data Index: 3917949 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3710. Min Range: -6.3710
Max Act: 5.9647. Min Act: -0.1700
Data Index: 5599569 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3710. Min Range: -6.3710
Max Act: 5.9335. Min Act: -0.1700
Data Index: 7737461 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3710. Min Range: -6.3710
Max Act: 5.9022. Min Act: -0.1700
Data Index: 3812998 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3710. Min Range: -6.3710
Max Act: 5.9335. Min Act: -0.1700
Data Index: 1516619 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3710. Min Range: -6.3710
Max Act: 5.9335. Min Act: -0.1700
Data Index: 5272168 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19