Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2216 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.4824. Min Range: -1.4824
Max Act: 1.4824. Min Act: -0.1700
Data Index: 611172 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4824. Min Range: -1.4824
Max Act: 1.4296. Min Act: -0.1700
Data Index: 8275857 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4824. Min Range: -1.4824
Max Act: 1.4296. Min Act: -0.1700
Data Index: 3146377 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4824. Min Range: -1.4824
Max Act: 1.4296. Min Act: -0.1700
Data Index: 7185768 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4824. Min Range: -1.4824
Max Act: 1.4120. Min Act: -0.1700
Data Index: 3146374 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4824. Min Range: -1.4824
Max Act: 1.4120. Min Act: -0.1700
Data Index: 2160912 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4824. Min Range: -1.4824
Max Act: 1.3591. Min Act: -0.1700
Data Index: 3146376 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4824. Min Range: -1.4824
Max Act: 1.3591. Min Act: -0.1700
Data Index: 3146378 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4824. Min Range: -1.4824
Max Act: 1.3591. Min Act: -0.1700
Data Index: 3146375 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4824. Min Range: -1.4824
Max Act: 1.3415. Min Act: -0.1700
Data Index: 1246515 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4824. Min Range: -1.4824
Max Act: 1.3415. Min Act: -0.1700
Data Index: 4799610 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4824. Min Range: -1.4824
Max Act: 1.3238. Min Act: -0.1700
Data Index: 2349368 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4824. Min Range: -1.4824
Max Act: 1.3238. Min Act: -0.1695
Data Index: 4031379 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4824. Min Range: -1.4824
Max Act: 1.3062. Min Act: -0.1700
Data Index: 7023612 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4824. Min Range: -1.4824
Max Act: 1.3062. Min Act: -0.1700
Data Index: 5694693 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4824. Min Range: -1.4824
Max Act: 1.3062. Min Act: -0.1700
Data Index: 10581 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4824. Min Range: -1.4824
Max Act: 1.3062. Min Act: -0.1700
Data Index: 8462724 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4824. Min Range: -1.4824
Max Act: 1.3062. Min Act: -0.1697
Data Index: 8721265 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4824. Min Range: -1.4824
Max Act: 1.3238. Min Act: -0.1700
Data Index: 7290596 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4824. Min Range: -1.4824
Max Act: 1.3062. Min Act: -0.1700
Data Index: 8769573 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19