Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3621 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0760. Min Range: -5.0760
Max Act: 5.0135. Min Act: -0.1700
Data Index: 6690614 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0760. Min Range: -5.0760
Max Act: 5.0760. Min Act: -0.1700
Data Index: 3080408 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0760. Min Range: -5.0760
Max Act: 4.9822. Min Act: -0.1700
Data Index: 416112 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0760. Min Range: -5.0760
Max Act: 4.9822. Min Act: -0.1700
Data Index: 6386875 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0760. Min Range: -5.0760
Max Act: 4.9510. Min Act: -0.1700
Data Index: 5582136 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0760. Min Range: -5.0760
Max Act: 5.0135. Min Act: -0.1700
Data Index: 4200264 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0760. Min Range: -5.0760
Max Act: 5.0760. Min Act: -0.1700
Data Index: 1709641 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0760. Min Range: -5.0760
Max Act: 4.9197. Min Act: -0.1700
Data Index: 4279610 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0760. Min Range: -5.0760
Max Act: 4.9510. Min Act: -0.1700
Data Index: 4115605 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0760. Min Range: -5.0760
Max Act: 4.9197. Min Act: -0.1700
Data Index: 3985205 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0760. Min Range: -5.0760
Max Act: 4.9510. Min Act: -0.1700
Data Index: 5605685 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0760. Min Range: -5.0760
Max Act: 4.9822. Min Act: -0.1700
Data Index: 3755861 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0760. Min Range: -5.0760
Max Act: 4.9822. Min Act: -0.1700
Data Index: 4778447 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0760. Min Range: -5.0760
Max Act: 4.9822. Min Act: -0.1700
Data Index: 7958858 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0760. Min Range: -5.0760
Max Act: 4.9197. Min Act: -0.1700
Data Index: 4724719 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0760. Min Range: -5.0760
Max Act: 4.9197. Min Act: -0.1700
Data Index: 4689648 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0760. Min Range: -5.0760
Max Act: 4.9510. Min Act: -0.1700
Data Index: 228002 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0760. Min Range: -5.0760
Max Act: 4.9197. Min Act: -0.1700
Data Index: 1310048 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0760. Min Range: -5.0760
Max Act: 4.9510. Min Act: -0.1700
Data Index: 4112164 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0760. Min Range: -5.0760
Max Act: 4.9510. Min Act: -0.1700
Data Index: 5429170 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19