Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5289 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1181. Min Range: -6.1181
Max Act: 6.1181. Min Act: -0.1700
Data Index: 3614998 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1181. Min Range: -6.1181
Max Act: 6.0556. Min Act: -0.1700
Data Index: 4156409 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.8056. Min Act: -0.1700
Data Index: 4513017 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7744. Min Act: -0.1700
Data Index: 3791235 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7119. Min Act: -0.1700
Data Index: 5378472 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7119. Min Act: -0.1700
Data Index: 3787412 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7119. Min Act: -0.1700
Data Index: 4396513 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7119. Min Act: -0.1700
Data Index: 6732092 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7119. Min Act: -0.1700
Data Index: 3570736 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7119. Min Act: -0.1700
Data Index: 3451005 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7119. Min Act: -0.1700
Data Index: 3180231 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7119. Min Act: -0.1700
Data Index: 8648397 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.6806. Min Act: -0.1700
Data Index: 2637491 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.6494. Min Act: -0.1700
Data Index: 2517071 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.6494. Min Act: -0.1700
Data Index: 8699565 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.6494. Min Act: -0.1700
Data Index: 7433176 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.6181. Min Act: -0.1700
Data Index: 252146 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.6181. Min Act: -0.1700
Data Index: 481034 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.6181. Min Act: -0.1700
Data Index: 1351829 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.6181. Min Act: -0.1700
Data Index: 8631897 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19