Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1953. Min Range: -7.1953
Max Act: 7.1953. Min Act: -0.1700
Data Index: 8448596 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1953. Min Range: -7.1953
Max Act: 7.1016. Min Act: -0.1700
Data Index: 3157769 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.7578. Min Act: -0.1700
Data Index: 1941213 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.6953. Min Act: -0.1700
Data Index: 1391161 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.6641. Min Act: -0.1700
Data Index: 1870887 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.6641. Min Act: -0.1700
Data Index: 7880324 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.6328. Min Act: -0.1700
Data Index: 6688947 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.5703. Min Act: -0.1700
Data Index: 2881137 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.5391. Min Act: -0.1700
Data Index: 8033300 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.5391. Min Act: -0.1700
Data Index: 1336565 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.5078. Min Act: -0.1700
Data Index: 2246943 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.5078. Min Act: -0.1700
Data Index: 3209072 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.5078. Min Act: -0.1700
Data Index: 5527885 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.5078. Min Act: -0.1700
Data Index: 5795003 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.4766. Min Act: -0.1700
Data Index: 7493255 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.4766. Min Act: -0.1700
Data Index: 1287530 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.4453. Min Act: -0.1700
Data Index: 4365538 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.4141. Min Act: -0.1700
Data Index: 3613720 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.3828. Min Act: -0.1700
Data Index: 6039391 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.3828. Min Act: -0.1700
Data Index: 3250442 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19