Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2365 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1364. Min Range: -3.1364
Max Act: 3.1364. Min Act: -0.1700
Data Index: 2339132 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1364. Min Range: -3.1364
Max Act: 2.8041. Min Act: -0.1700
Data Index: 2292888 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1364. Min Range: -3.1364
Max Act: 2.8200. Min Act: -0.1700
Data Index: 4003934 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1364. Min Range: -3.1364
Max Act: 2.7881. Min Act: -0.1700
Data Index: 1916814 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1364. Min Range: -3.1364
Max Act: 2.7563. Min Act: -0.1700
Data Index: 4267785 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1364. Min Range: -3.1364
Max Act: 2.6923. Min Act: -0.1700
Data Index: 3487753 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1364. Min Range: -3.1364
Max Act: 2.7083. Min Act: -0.1700
Data Index: 4267784 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1364. Min Range: -3.1364
Max Act: 2.7083. Min Act: -0.1700
Data Index: 4223646 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1364. Min Range: -3.1364
Max Act: 2.7243. Min Act: -0.1700
Data Index: 6559536 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1364. Min Range: -3.1364
Max Act: 2.6923. Min Act: -0.1700
Data Index: 4918590 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1364. Min Range: -3.1364
Max Act: 2.6763. Min Act: -0.1700
Data Index: 1369081 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1364. Min Range: -3.1364
Max Act: 2.6763. Min Act: -0.1700
Data Index: 2962613 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1364. Min Range: -3.1364
Max Act: 2.6923. Min Act: -0.1700
Data Index: 184153 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1364. Min Range: -3.1364
Max Act: 2.6763. Min Act: -0.1700
Data Index: 1743751 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1364. Min Range: -3.1364
Max Act: 2.6763. Min Act: -0.1700
Data Index: 3360934 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1364. Min Range: -3.1364
Max Act: 2.6603. Min Act: -0.1700
Data Index: 1426619 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1364. Min Range: -3.1364
Max Act: 2.6763. Min Act: -0.1700
Data Index: 5023214 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1364. Min Range: -3.1364
Max Act: 2.6763. Min Act: -0.1700
Data Index: 3201321 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1364. Min Range: -3.1364
Max Act: 2.6603. Min Act: -0.1700
Data Index: 7375178 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1364. Min Range: -3.1364
Max Act: 2.6603. Min Act: -0.1700
Data Index: 8286448 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19