Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3464 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7987. Min Range: -7.7987
Max Act: 7.7987. Min Act: -0.1700
Data Index: 2164420 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7987. Min Range: -7.7987
Max Act: 7.6112. Min Act: -0.1700
Data Index: 1569538 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7987. Min Range: -7.7987
Max Act: 7.5800. Min Act: -0.1700
Data Index: 6323755 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7987. Min Range: -7.7987
Max Act: 7.5175. Min Act: -0.1700
Data Index: 1115004 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7987. Min Range: -7.7987
Max Act: 7.4550. Min Act: -0.1700
Data Index: 8445809 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7987. Min Range: -7.7987
Max Act: 7.4862. Min Act: -0.1700
Data Index: 6716734 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7987. Min Range: -7.7987
Max Act: 7.4550. Min Act: -0.1700
Data Index: 1714221 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7987. Min Range: -7.7987
Max Act: 7.4550. Min Act: -0.1700
Data Index: 1333492 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7987. Min Range: -7.7987
Max Act: 7.4550. Min Act: -0.1700
Data Index: 8022826 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7987. Min Range: -7.7987
Max Act: 7.4237. Min Act: -0.1700
Data Index: 2992134 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7987. Min Range: -7.7987
Max Act: 7.3612. Min Act: -0.1700
Data Index: 5082243 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7987. Min Range: -7.7987
Max Act: 7.3612. Min Act: -0.1700
Data Index: 6902698 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7987. Min Range: -7.7987
Max Act: 7.3300. Min Act: -0.1700
Data Index: 6351182 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7987. Min Range: -7.7987
Max Act: 7.3612. Min Act: -0.1700
Data Index: 5189255 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7987. Min Range: -7.7987
Max Act: 7.2675. Min Act: -0.1700
Data Index: 5444839 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7987. Min Range: -7.7987
Max Act: 7.2675. Min Act: -0.1700
Data Index: 8163060 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7987. Min Range: -7.7987
Max Act: 7.2362. Min Act: -0.1700
Data Index: 2109381 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7987. Min Range: -7.7987
Max Act: 7.2050. Min Act: -0.1700
Data Index: 8068948 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7987. Min Range: -7.7987
Max Act: 7.1737. Min Act: -0.1700
Data Index: 6472636 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7987. Min Range: -7.7987
Max Act: 7.1737. Min Act: -0.1700
Data Index: 6460430 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19