Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3187 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.4544. Min Act: -0.1700
Data Index: 5681590 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.3918. Min Act: -0.1700
Data Index: 214307 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.2356. Min Act: -0.1700
Data Index: 923406 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.2043. Min Act: -0.1700
Data Index: 4353221 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.1731. Min Act: -0.1700
Data Index: 7078353 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.0793. Min Act: -0.1700
Data Index: 8805470 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.0481. Min Act: -0.1700
Data Index: 2912053 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.0168. Min Act: -0.1700
Data Index: 5080693 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4544. Min Range: -4.4544
Max Act: 3.9855. Min Act: -0.1700
Data Index: 2834138 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4544. Min Range: -4.4544
Max Act: 3.9855. Min Act: -0.1700
Data Index: 5155501 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4544. Min Range: -4.4544
Max Act: 3.9543. Min Act: -0.1700
Data Index: 1394423 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4544. Min Range: -4.4544
Max Act: 3.9230. Min Act: -0.1700
Data Index: 1221497 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4544. Min Range: -4.4544
Max Act: 3.9230. Min Act: -0.1700
Data Index: 1275742 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4544. Min Range: -4.4544
Max Act: 3.9230. Min Act: -0.1700
Data Index: 5205445 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4544. Min Range: -4.4544
Max Act: 3.8917. Min Act: -0.1700
Data Index: 4372195 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4544. Min Range: -4.4544
Max Act: 3.8917. Min Act: -0.1700
Data Index: 4377856 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4544. Min Range: -4.4544
Max Act: 3.8917. Min Act: -0.1700
Data Index: 2834139 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4544. Min Range: -4.4544
Max Act: 3.8917. Min Act: -0.1700
Data Index: 1472998 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4544. Min Range: -4.4544
Max Act: 3.8605. Min Act: -0.1700
Data Index: 1014266 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4544. Min Range: -4.4544
Max Act: 3.8917. Min Act: -0.1700
Data Index: 5124089 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19