Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2246 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4936. Min Range: -4.4936
Max Act: 4.4936. Min Act: -0.1700
Data Index: 2420173 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4936. Min Range: -4.4936
Max Act: 4.3373. Min Act: -0.1700
Data Index: 3229053 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4936. Min Range: -4.4936
Max Act: 4.3061. Min Act: -0.1700
Data Index: 2097935 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4936. Min Range: -4.4936
Max Act: 4.1810. Min Act: -0.1700
Data Index: 3538745 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4936. Min Range: -4.4936
Max Act: 4.1498. Min Act: -0.1700
Data Index: 1283292 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4936. Min Range: -4.4936
Max Act: 4.1185. Min Act: -0.1700
Data Index: 3599002 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4936. Min Range: -4.4936
Max Act: 4.1185. Min Act: -0.1700
Data Index: 5286117 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4936. Min Range: -4.4936
Max Act: 4.0873. Min Act: -0.1700
Data Index: 4502057 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4936. Min Range: -4.4936
Max Act: 4.1185. Min Act: -0.1700
Data Index: 1795369 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4936. Min Range: -4.4936
Max Act: 4.0873. Min Act: -0.1700
Data Index: 5117349 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4936. Min Range: -4.4936
Max Act: 4.0560. Min Act: -0.1700
Data Index: 7300066 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4936. Min Range: -4.4936
Max Act: 4.0873. Min Act: -0.1700
Data Index: 3214442 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4936. Min Range: -4.4936
Max Act: 4.0873. Min Act: -0.1700
Data Index: 1312157 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4936. Min Range: -4.4936
Max Act: 4.0560. Min Act: -0.1700
Data Index: 562712 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4936. Min Range: -4.4936
Max Act: 4.0248. Min Act: -0.1700
Data Index: 1829511 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4936. Min Range: -4.4936
Max Act: 4.0560. Min Act: -0.1700
Data Index: 4568674 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4936. Min Range: -4.4936
Max Act: 4.0560. Min Act: -0.1700
Data Index: 3214439 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4936. Min Range: -4.4936
Max Act: 4.0560. Min Act: -0.1700
Data Index: 2168473 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4936. Min Range: -4.4936
Max Act: 4.0248. Min Act: -0.1700
Data Index: 2363286 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4936. Min Range: -4.4936
Max Act: 4.0248. Min Act: -0.1700
Data Index: 1793954 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19