Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3468 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.5402. Min Range: -1.5402
Max Act: 1.5402. Min Act: -0.1700
Data Index: 4351858 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5402. Min Range: -1.5402
Max Act: 1.5402. Min Act: -0.1700
Data Index: 7272580 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5402. Min Range: -1.5402
Max Act: 1.5227. Min Act: -0.1700
Data Index: 5886070 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5402. Min Range: -1.5402
Max Act: 1.5052. Min Act: -0.1700
Data Index: 7806543 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5402. Min Range: -1.5402
Max Act: 1.5052. Min Act: -0.1700
Data Index: 1285418 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5402. Min Range: -1.5402
Max Act: 1.5052. Min Act: -0.1700
Data Index: 4812597 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5402. Min Range: -1.5402
Max Act: 1.5052. Min Act: -0.1700
Data Index: 8347615 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5402. Min Range: -1.5402
Max Act: 1.5052. Min Act: -0.1700
Data Index: 7969295 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5402. Min Range: -1.5402
Max Act: 1.4876. Min Act: -0.1700
Data Index: 3299769 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5402. Min Range: -1.5402
Max Act: 1.4876. Min Act: -0.1700
Data Index: 764454 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5402. Min Range: -1.5402
Max Act: 1.4700. Min Act: -0.1700
Data Index: 5734329 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5402. Min Range: -1.5402
Max Act: 1.4700. Min Act: -0.1700
Data Index: 7542380 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5402. Min Range: -1.5402
Max Act: 1.4524. Min Act: -0.1700
Data Index: 1900131 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5402. Min Range: -1.5402
Max Act: 1.4524. Min Act: -0.1700
Data Index: 3649129 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5402. Min Range: -1.5402
Max Act: 1.4524. Min Act: -0.1700
Data Index: 1285424 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5402. Min Range: -1.5402
Max Act: 1.4348. Min Act: -0.1700
Data Index: 3148415 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5402. Min Range: -1.5402
Max Act: 1.4348. Min Act: -0.1700
Data Index: 6523455 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5402. Min Range: -1.5402
Max Act: 1.4348. Min Act: -0.1700
Data Index: 8501571 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5402. Min Range: -1.5402
Max Act: 1.4348. Min Act: -0.1700
Data Index: 6508230 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5402. Min Range: -1.5402
Max Act: 1.4524. Min Act: -0.1700
Data Index: 2258645 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19