Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1185 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1942. Min Range: -8.1942
Max Act: 8.1942. Min Act: -0.1700
Data Index: 5691164 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1942. Min Range: -8.1942
Max Act: 8.1942. Min Act: -0.1700
Data Index: 1788531 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1942. Min Range: -8.1942
Max Act: 7.9442. Min Act: -0.1700
Data Index: 2442931 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1942. Min Range: -8.1942
Max Act: 7.6942. Min Act: -0.1700
Data Index: 1935388 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1942. Min Range: -8.1942
Max Act: 7.6004. Min Act: -0.1700
Data Index: 1288148 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1942. Min Range: -8.1942
Max Act: 7.6317. Min Act: -0.1700
Data Index: 4880625 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1942. Min Range: -8.1942
Max Act: 7.6317. Min Act: -0.1700
Data Index: 4421190 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1942. Min Range: -8.1942
Max Act: 7.6004. Min Act: -0.1700
Data Index: 153209 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1942. Min Range: -8.1942
Max Act: 7.5692. Min Act: -0.1700
Data Index: 5357731 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1942. Min Range: -8.1942
Max Act: 7.5379. Min Act: -0.1700
Data Index: 835547 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1942. Min Range: -8.1942
Max Act: 7.5379. Min Act: -0.1700
Data Index: 7976223 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1942. Min Range: -8.1942
Max Act: 7.5067. Min Act: -0.1700
Data Index: 121297 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1942. Min Range: -8.1942
Max Act: 7.4442. Min Act: -0.1700
Data Index: 4898069 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1942. Min Range: -8.1942
Max Act: 7.4442. Min Act: -0.1700
Data Index: 4414617 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1942. Min Range: -8.1942
Max Act: 7.4129. Min Act: -0.1700
Data Index: 4449828 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1942. Min Range: -8.1942
Max Act: 7.3817. Min Act: -0.1700
Data Index: 4687215 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1942. Min Range: -8.1942
Max Act: 7.3817. Min Act: -0.1700
Data Index: 936484 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1942. Min Range: -8.1942
Max Act: 7.3504. Min Act: -0.1700
Data Index: 5462906 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1942. Min Range: -8.1942
Max Act: 7.3504. Min Act: -0.1700
Data Index: 1624582 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1942. Min Range: -8.1942
Max Act: 7.3504. Min Act: -0.1700
Data Index: 190976 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19