Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4938 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7451. Min Range: -4.7451
Max Act: 4.7451. Min Act: -0.1700
Data Index: 3346385 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7451. Min Range: -4.7451
Max Act: 4.7451. Min Act: -0.1700
Data Index: 8745820 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7451. Min Range: -4.7451
Max Act: 4.7451. Min Act: -0.1700
Data Index: 1254080 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7451. Min Range: -4.7451
Max Act: 4.6514. Min Act: -0.1700
Data Index: 6462132 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7451. Min Range: -4.7451
Max Act: 4.6826. Min Act: -0.1700
Data Index: 2280767 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7451. Min Range: -4.7451
Max Act: 4.6826. Min Act: -0.1700
Data Index: 6132164 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7451. Min Range: -4.7451
Max Act: 4.6514. Min Act: -0.1700
Data Index: 8745812 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7451. Min Range: -4.7451
Max Act: 4.6201. Min Act: -0.1700
Data Index: 5558964 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7451. Min Range: -4.7451
Max Act: 4.5889. Min Act: -0.1700
Data Index: 8136537 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7451. Min Range: -4.7451
Max Act: 4.5889. Min Act: -0.1700
Data Index: 2225300 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7451. Min Range: -4.7451
Max Act: 4.5889. Min Act: -0.1700
Data Index: 6132159 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7451. Min Range: -4.7451
Max Act: 4.5889. Min Act: -0.1700
Data Index: 2077067 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7451. Min Range: -4.7451
Max Act: 4.5889. Min Act: -0.1700
Data Index: 2077065 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7451. Min Range: -4.7451
Max Act: 4.5576. Min Act: -0.1700
Data Index: 34962 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7451. Min Range: -4.7451
Max Act: 4.5576. Min Act: -0.1700
Data Index: 4679219 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7451. Min Range: -4.7451
Max Act: 4.5576. Min Act: -0.1700
Data Index: 6315569 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7451. Min Range: -4.7451
Max Act: 4.5576. Min Act: -0.1700
Data Index: 4809588 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7451. Min Range: -4.7451
Max Act: 4.5264. Min Act: -0.1700
Data Index: 4781962 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7451. Min Range: -4.7451
Max Act: 4.5264. Min Act: -0.1700
Data Index: 38193 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7451. Min Range: -4.7451
Max Act: 4.5264. Min Act: -0.1700
Data Index: 1159022 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19