Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2183 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.0232. Min Range: -10.0232
Max Act: 10.0232. Min Act: -0.1700
Data Index: 8098247 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0232. Min Range: -10.0232
Max Act: 9.1482. Min Act: -0.1700
Data Index: 7243421 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0232. Min Range: -10.0232
Max Act: 9.0232. Min Act: -0.1700
Data Index: 8688775 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0232. Min Range: -10.0232
Max Act: 9.0232. Min Act: -0.1700
Data Index: 2139069 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0232. Min Range: -10.0232
Max Act: 9.0232. Min Act: -0.1700
Data Index: 2777802 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0232. Min Range: -10.0232
Max Act: 9.0232. Min Act: -0.1700
Data Index: 1955786 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0232. Min Range: -10.0232
Max Act: 8.9607. Min Act: -0.1699
Data Index: 4042939 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0232. Min Range: -10.0232
Max Act: 8.8357. Min Act: -0.1700
Data Index: 4747947 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0232. Min Range: -10.0232
Max Act: 8.8357. Min Act: -0.1700
Data Index: 6388819 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0232. Min Range: -10.0232
Max Act: 8.7732. Min Act: -0.1700
Data Index: 5158010 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0232. Min Range: -10.0232
Max Act: 8.7732. Min Act: -0.1700
Data Index: 3178303 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0232. Min Range: -10.0232
Max Act: 8.7732. Min Act: -0.1700
Data Index: 2777804 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0232. Min Range: -10.0232
Max Act: 8.7107. Min Act: -0.1700
Data Index: 55712 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0232. Min Range: -10.0232
Max Act: 8.6482. Min Act: -0.1700
Data Index: 3564874 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0232. Min Range: -10.0232
Max Act: 8.6482. Min Act: -0.1700
Data Index: 2412919 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0232. Min Range: -10.0232
Max Act: 8.6482. Min Act: -0.1700
Data Index: 169770 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0232. Min Range: -10.0232
Max Act: 8.5857. Min Act: -0.1700
Data Index: 7758443 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0232. Min Range: -10.0232
Max Act: 8.5857. Min Act: -0.1700
Data Index: 4164618 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0232. Min Range: -10.0232
Max Act: 8.5857. Min Act: -0.1700
Data Index: 4620582 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0232. Min Range: -10.0232
Max Act: 8.5857. Min Act: -0.1700
Data Index: 4234767 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19