Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2896 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3808. Min Range: -7.3808
Max Act: 7.3808. Min Act: -0.1700
Data Index: 7860911 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3808. Min Range: -7.3808
Max Act: 7.2558. Min Act: -0.1700
Data Index: 4291914 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3808. Min Range: -7.3808
Max Act: 7.1933. Min Act: -0.1700
Data Index: 5663032 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3808. Min Range: -7.3808
Max Act: 7.1621. Min Act: -0.1700
Data Index: 930796 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3808. Min Range: -7.3808
Max Act: 7.1308. Min Act: -0.1700
Data Index: 1110988 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3808. Min Range: -7.3808
Max Act: 6.9433. Min Act: -0.1700
Data Index: 8186263 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3808. Min Range: -7.3808
Max Act: 6.8496. Min Act: -0.1700
Data Index: 8387763 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3808. Min Range: -7.3808
Max Act: 6.8496. Min Act: -0.1700
Data Index: 484330 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3808. Min Range: -7.3808
Max Act: 6.8808. Min Act: -0.1700
Data Index: 1416276 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3808. Min Range: -7.3808
Max Act: 6.8183. Min Act: -0.1700
Data Index: 3192272 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3808. Min Range: -7.3808
Max Act: 6.7871. Min Act: -0.1700
Data Index: 5070846 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3808. Min Range: -7.3808
Max Act: 6.7558. Min Act: -0.1700
Data Index: 5563713 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3808. Min Range: -7.3808
Max Act: 6.7246. Min Act: -0.1700
Data Index: 1110989 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3808. Min Range: -7.3808
Max Act: 6.7558. Min Act: -0.1700
Data Index: 1792597 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3808. Min Range: -7.3808
Max Act: 6.7558. Min Act: -0.1700
Data Index: 8181300 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3808. Min Range: -7.3808
Max Act: 6.7558. Min Act: -0.1700
Data Index: 7514076 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3808. Min Range: -7.3808
Max Act: 6.7246. Min Act: -0.1700
Data Index: 679081 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3808. Min Range: -7.3808
Max Act: 6.7246. Min Act: -0.1700
Data Index: 623298 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3808. Min Range: -7.3808
Max Act: 6.7246. Min Act: -0.1700
Data Index: 4646618 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3808. Min Range: -7.3808
Max Act: 6.7558. Min Act: -0.1700
Data Index: 5404343 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19