Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 745 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4951. Min Range: -8.4951
Max Act: 8.4951. Min Act: -0.1700
Data Index: 4734326 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4951. Min Range: -8.4951
Max Act: 8.3701. Min Act: -0.1700
Data Index: 3387380 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4951. Min Range: -8.4951
Max Act: 8.3076. Min Act: -0.1700
Data Index: 4931304 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4951. Min Range: -8.4951
Max Act: 8.3076. Min Act: -0.1700
Data Index: 8035212 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4951. Min Range: -8.4951
Max Act: 8.2451. Min Act: -0.1700
Data Index: 7058664 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4951. Min Range: -8.4951
Max Act: 8.2451. Min Act: -0.1700
Data Index: 2318434 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4951. Min Range: -8.4951
Max Act: 8.1826. Min Act: -0.1700
Data Index: 3830469 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4951. Min Range: -8.4951
Max Act: 8.2451. Min Act: -0.1700
Data Index: 5176588 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4951. Min Range: -8.4951
Max Act: 8.1826. Min Act: -0.1700
Data Index: 818336 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4951. Min Range: -8.4951
Max Act: 8.0576. Min Act: -0.1700
Data Index: 3396292 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4951. Min Range: -8.4951
Max Act: 8.0576. Min Act: -0.1700
Data Index: 7684899 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4951. Min Range: -8.4951
Max Act: 8.0576. Min Act: -0.1700
Data Index: 5983003 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4951. Min Range: -8.4951
Max Act: 8.0576. Min Act: -0.1700
Data Index: 1677896 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4951. Min Range: -8.4951
Max Act: 8.0576. Min Act: -0.1700
Data Index: 5673363 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4951. Min Range: -8.4951
Max Act: 8.0576. Min Act: -0.1700
Data Index: 5003948 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4951. Min Range: -8.4951
Max Act: 8.0576. Min Act: -0.1700
Data Index: 7179704 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4951. Min Range: -8.4951
Max Act: 8.0576. Min Act: -0.1700
Data Index: 6632647 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4951. Min Range: -8.4951
Max Act: 8.0263. Min Act: -0.1700
Data Index: 1940918 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4951. Min Range: -8.4951
Max Act: 7.9951. Min Act: -0.1700
Data Index: 7980714 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4951. Min Range: -8.4951
Max Act: 7.9951. Min Act: -0.1700
Data Index: 2638101 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19