Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3644 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3560. Min Range: -2.3560
Max Act: 2.3560. Min Act: -0.1700
Data Index: 1235174 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3560. Min Range: -2.3560
Max Act: 2.2904. Min Act: -0.1700
Data Index: 3385973 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3560. Min Range: -2.3560
Max Act: 2.2739. Min Act: -0.1700
Data Index: 4030072 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3560. Min Range: -2.3560
Max Act: 2.2739. Min Act: -0.1700
Data Index: 541141 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3560. Min Range: -2.3560
Max Act: 2.2574. Min Act: -0.1700
Data Index: 1844945 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3560. Min Range: -2.3560
Max Act: 2.2409. Min Act: -0.1700
Data Index: 4695234 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3560. Min Range: -2.3560
Max Act: 2.2243. Min Act: -0.1700
Data Index: 4490196 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3560. Min Range: -2.3560
Max Act: 2.1912. Min Act: -0.1700
Data Index: 1402419 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3560. Min Range: -2.3560
Max Act: 2.1745. Min Act: -0.1700
Data Index: 1260681 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3560. Min Range: -2.3560
Max Act: 2.1745. Min Act: -0.1700
Data Index: 541140 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3560. Min Range: -2.3560
Max Act: 2.1745. Min Act: -0.1700
Data Index: 8018685 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3560. Min Range: -2.3560
Max Act: 2.1579. Min Act: -0.1700
Data Index: 609536 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3560. Min Range: -2.3560
Max Act: 2.1579. Min Act: -0.1700
Data Index: 8257504 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3560. Min Range: -2.3560
Max Act: 2.1412. Min Act: -0.1700
Data Index: 5150493 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3560. Min Range: -2.3560
Max Act: 2.1579. Min Act: -0.1700
Data Index: 5746073 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3560. Min Range: -2.3560
Max Act: 2.1579. Min Act: -0.1700
Data Index: 2766124 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3560. Min Range: -2.3560
Max Act: 2.1412. Min Act: -0.1700
Data Index: 1893116 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3560. Min Range: -2.3560
Max Act: 2.1412. Min Act: -0.1700
Data Index: 2315764 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3560. Min Range: -2.3560
Max Act: 2.1412. Min Act: -0.1700
Data Index: 6085036 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3560. Min Range: -2.3560
Max Act: 2.1245. Min Act: -0.1700
Data Index: 6608002 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19