Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3372 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8580. Min Range: -5.8580
Max Act: 5.8580. Min Act: -0.1700
Data Index: 7013064 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8580. Min Range: -5.8580
Max Act: 5.3580. Min Act: -0.1700
Data Index: 7854181 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8580. Min Range: -5.8580
Max Act: 5.3267. Min Act: -0.1700
Data Index: 986598 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8580. Min Range: -5.8580
Max Act: 5.3267. Min Act: -0.1700
Data Index: 8271618 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8580. Min Range: -5.8580
Max Act: 5.2955. Min Act: -0.1700
Data Index: 6947915 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8580. Min Range: -5.8580
Max Act: 5.2330. Min Act: -0.1700
Data Index: 6502436 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8580. Min Range: -5.8580
Max Act: 5.2642. Min Act: -0.1700
Data Index: 6824290 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8580. Min Range: -5.8580
Max Act: 5.2017. Min Act: -0.1700
Data Index: 8430896 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8580. Min Range: -5.8580
Max Act: 5.1392. Min Act: -0.1700
Data Index: 2519173 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8580. Min Range: -5.8580
Max Act: 5.2017. Min Act: -0.1700
Data Index: 3001541 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8580. Min Range: -5.8580
Max Act: 5.1705. Min Act: -0.1700
Data Index: 4035951 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8580. Min Range: -5.8580
Max Act: 5.1705. Min Act: -0.1700
Data Index: 1058403 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8580. Min Range: -5.8580
Max Act: 5.1080. Min Act: -0.1700
Data Index: 6111450 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8580. Min Range: -5.8580
Max Act: 5.0767. Min Act: -0.1700
Data Index: 5018754 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8580. Min Range: -5.8580
Max Act: 5.0142. Min Act: -0.1700
Data Index: 3946067 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8580. Min Range: -5.8580
Max Act: 4.9830. Min Act: -0.1700
Data Index: 3639853 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8580. Min Range: -5.8580
Max Act: 4.9205. Min Act: -0.1700
Data Index: 6918477 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8580. Min Range: -5.8580
Max Act: 4.9830. Min Act: -0.1700
Data Index: 8013119 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8580. Min Range: -5.8580
Max Act: 4.9517. Min Act: -0.1700
Data Index: 6924022 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8580. Min Range: -5.8580
Max Act: 4.9517. Min Act: -0.1700
Data Index: 6541054 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19