Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3728 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3306. Min Range: -4.3306
Max Act: 4.3306. Min Act: -0.1700
Data Index: 550373 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3306. Min Range: -4.3306
Max Act: 4.2368. Min Act: -0.1700
Data Index: 5320640 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3306. Min Range: -4.3306
Max Act: 4.2368. Min Act: -0.1700
Data Index: 5077905 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3306. Min Range: -4.3306
Max Act: 4.2056. Min Act: -0.1700
Data Index: 3760474 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3306. Min Range: -4.3306
Max Act: 4.2056. Min Act: -0.1700
Data Index: 1816565 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3306. Min Range: -4.3306
Max Act: 4.1743. Min Act: -0.1700
Data Index: 7168228 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3306. Min Range: -4.3306
Max Act: 4.1431. Min Act: -0.1700
Data Index: 7458222 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3306. Min Range: -4.3306
Max Act: 4.1431. Min Act: -0.1700
Data Index: 4507807 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3306. Min Range: -4.3306
Max Act: 4.1431. Min Act: -0.1700
Data Index: 8225029 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3306. Min Range: -4.3306
Max Act: 4.0806. Min Act: -0.1700
Data Index: 8804887 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3306. Min Range: -4.3306
Max Act: 4.0806. Min Act: -0.1700
Data Index: 4321383 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3306. Min Range: -4.3306
Max Act: 4.0806. Min Act: -0.1700
Data Index: 2922784 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3306. Min Range: -4.3306
Max Act: 4.0493. Min Act: -0.1700
Data Index: 5594725 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3306. Min Range: -4.3306
Max Act: 4.0806. Min Act: -0.1700
Data Index: 3734175 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3306. Min Range: -4.3306
Max Act: 4.0493. Min Act: -0.1700
Data Index: 4444968 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3306. Min Range: -4.3306
Max Act: 4.0493. Min Act: -0.1700
Data Index: 5619018 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3306. Min Range: -4.3306
Max Act: 4.0493. Min Act: -0.1700
Data Index: 7039879 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3306. Min Range: -4.3306
Max Act: 4.0493. Min Act: -0.1700
Data Index: 2322813 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3306. Min Range: -4.3306
Max Act: 4.0493. Min Act: -0.1700
Data Index: 3230046 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3306. Min Range: -4.3306
Max Act: 4.0493. Min Act: -0.1700
Data Index: 6400243 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19