Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6255 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5334. Min Range: -6.5334
Max Act: 6.5334. Min Act: -0.1700
Data Index: 4022107 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5334. Min Range: -6.5334
Max Act: 6.4084. Min Act: -0.1700
Data Index: 5851244 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5334. Min Range: -6.5334
Max Act: 6.4084. Min Act: -0.1700
Data Index: 7768399 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5334. Min Range: -6.5334
Max Act: 6.3772. Min Act: -0.1700
Data Index: 4599492 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5334. Min Range: -6.5334
Max Act: 6.2834. Min Act: -0.1700
Data Index: 8154020 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5334. Min Range: -6.5334
Max Act: 6.2209. Min Act: -0.1700
Data Index: 5415009 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5334. Min Range: -6.5334
Max Act: 6.1272. Min Act: -0.1700
Data Index: 2211434 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5334. Min Range: -6.5334
Max Act: 6.1897. Min Act: -0.1700
Data Index: 7477693 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5334. Min Range: -6.5334
Max Act: 6.1584. Min Act: -0.1700
Data Index: 4878157 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5334. Min Range: -6.5334
Max Act: 6.1584. Min Act: -0.1700
Data Index: 4326058 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5334. Min Range: -6.5334
Max Act: 6.0959. Min Act: -0.1700
Data Index: 6117537 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5334. Min Range: -6.5334
Max Act: 6.0334. Min Act: -0.1700
Data Index: 3731971 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5334. Min Range: -6.5334
Max Act: 6.0334. Min Act: -0.1700
Data Index: 1746196 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5334. Min Range: -6.5334
Max Act: 6.0334. Min Act: -0.1700
Data Index: 8567983 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5334. Min Range: -6.5334
Max Act: 6.0022. Min Act: -0.1700
Data Index: 95644 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5334. Min Range: -6.5334
Max Act: 6.0334. Min Act: -0.1700
Data Index: 2439737 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5334. Min Range: -6.5334
Max Act: 5.9709. Min Act: -0.1700
Data Index: 1392926 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5334. Min Range: -6.5334
Max Act: 6.0022. Min Act: -0.1700
Data Index: 5930631 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5334. Min Range: -6.5334
Max Act: 6.0022. Min Act: -0.1700
Data Index: 1071177 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5334. Min Range: -6.5334
Max Act: 6.0022. Min Act: -0.1700
Data Index: 7538403 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19