Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4688 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0139. Min Range: -4.0139
Max Act: 4.0139. Min Act: -0.1700
Data Index: 1519585 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0139. Min Range: -4.0139
Max Act: 4.0139. Min Act: -0.1700
Data Index: 1684458 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0139. Min Range: -4.0139
Max Act: 3.9826. Min Act: -0.1700
Data Index: 4964296 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0139. Min Range: -4.0139
Max Act: 3.9513. Min Act: -0.1700
Data Index: 1755119 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0139. Min Range: -4.0139
Max Act: 3.8888. Min Act: -0.1700
Data Index: 7737360 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0139. Min Range: -4.0139
Max Act: 3.8575. Min Act: -0.1700
Data Index: 2083330 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0139. Min Range: -4.0139
Max Act: 3.8732. Min Act: -0.1700
Data Index: 4761382 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0139. Min Range: -4.0139
Max Act: 3.8575. Min Act: -0.1700
Data Index: 4098721 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0139. Min Range: -4.0139
Max Act: 3.8419. Min Act: -0.1700
Data Index: 3605613 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0139. Min Range: -4.0139
Max Act: 3.8575. Min Act: -0.1700
Data Index: 1324879 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0139. Min Range: -4.0139
Max Act: 3.8106. Min Act: -0.1700
Data Index: 8752699 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0139. Min Range: -4.0139
Max Act: 3.8106. Min Act: -0.1700
Data Index: 937313 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0139. Min Range: -4.0139
Max Act: 3.7950. Min Act: -0.1700
Data Index: 667544 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0139. Min Range: -4.0139
Max Act: 3.7950. Min Act: -0.1700
Data Index: 369269 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0139. Min Range: -4.0139
Max Act: 3.7794. Min Act: -0.1700
Data Index: 3499927 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0139. Min Range: -4.0139
Max Act: 3.7637. Min Act: -0.1700
Data Index: 6632503 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0139. Min Range: -4.0139
Max Act: 3.7794. Min Act: -0.1700
Data Index: 1406594 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0139. Min Range: -4.0139
Max Act: 3.7637. Min Act: -0.1700
Data Index: 763510 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0139. Min Range: -4.0139
Max Act: 3.7637. Min Act: -0.1700
Data Index: 4734131 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0139. Min Range: -4.0139
Max Act: 3.7637. Min Act: -0.1700
Data Index: 8166049 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19