Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1607 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0650. Min Range: -5.0650
Max Act: 5.0650. Min Act: -0.1700
Data Index: 6104709 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0650. Min Range: -5.0650
Max Act: 5.0650. Min Act: -0.1700
Data Index: 1632103 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0650. Min Range: -5.0650
Max Act: 5.0650. Min Act: -0.1700
Data Index: 2344883 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0650. Min Range: -5.0650
Max Act: 5.0025. Min Act: -0.1700
Data Index: 3761228 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0650. Min Range: -5.0650
Max Act: 5.0337. Min Act: -0.1700
Data Index: 6210850 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0650. Min Range: -5.0650
Max Act: 5.0337. Min Act: -0.1700
Data Index: 3478601 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.9712. Min Act: -0.1700
Data Index: 7078482 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.9712. Min Act: -0.1700
Data Index: 4563199 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.9400. Min Act: -0.1700
Data Index: 2736876 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.9400. Min Act: -0.1700
Data Index: 2810203 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.9400. Min Act: -0.1700
Data Index: 6178544 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.9712. Min Act: -0.1700
Data Index: 754098 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.9400. Min Act: -0.1700
Data Index: 8667598 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.9400. Min Act: -0.1700
Data Index: 330401 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.9400. Min Act: -0.1700
Data Index: 7313415 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.9087. Min Act: -0.1700
Data Index: 2711966 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.9087. Min Act: -0.1700
Data Index: 6989771 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.9087. Min Act: -0.1700
Data Index: 299435 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.9400. Min Act: -0.1700
Data Index: 1830059 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.9087. Min Act: -0.1700
Data Index: 1322256 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19