Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2023 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2900. Min Range: -4.2900
Max Act: 4.2900. Min Act: -0.1700
Data Index: 6523792 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2900. Min Range: -4.2900
Max Act: 4.2588. Min Act: -0.1700
Data Index: 3480091 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2900. Min Range: -4.2900
Max Act: 4.1337. Min Act: -0.1700
Data Index: 7462029 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2900. Min Range: -4.2900
Max Act: 4.0400. Min Act: -0.1700
Data Index: 1635511 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2900. Min Range: -4.2900
Max Act: 4.0712. Min Act: -0.1700
Data Index: 7462031 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2900. Min Range: -4.2900
Max Act: 4.0400. Min Act: -0.1700
Data Index: 3487361 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2900. Min Range: -4.2900
Max Act: 4.0400. Min Act: -0.1700
Data Index: 6058842 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.9775. Min Act: -0.1700
Data Index: 5824901 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.9618. Min Act: -0.1700
Data Index: 7462027 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.9462. Min Act: -0.1700
Data Index: 7462028 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.9306. Min Act: -0.1700
Data Index: 4051386 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.9149. Min Act: -0.1700
Data Index: 3361583 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.8837. Min Act: -0.1700
Data Index: 6315469 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.8837. Min Act: -0.1700
Data Index: 7462033 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.8993. Min Act: -0.1700
Data Index: 4344161 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.8837. Min Act: -0.1700
Data Index: 3368011 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.8680. Min Act: -0.1700
Data Index: 3474195 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.8211. Min Act: -0.1700
Data Index: 1814359 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.8524. Min Act: -0.1700
Data Index: 3707742 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.8368. Min Act: -0.1700
Data Index: 7642000 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19