Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2740 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7299. Min Range: -6.7299
Max Act: 6.7299. Min Act: -0.1700
Data Index: 1386387 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7299. Min Range: -6.7299
Max Act: 6.6674. Min Act: -0.1700
Data Index: 4586110 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7299. Min Range: -6.7299
Max Act: 6.6362. Min Act: -0.1700
Data Index: 8116262 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7299. Min Range: -6.7299
Max Act: 6.6049. Min Act: -0.1700
Data Index: 3623190 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7299. Min Range: -6.7299
Max Act: 6.4799. Min Act: -0.1700
Data Index: 7576672 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7299. Min Range: -6.7299
Max Act: 6.4799. Min Act: -0.1700
Data Index: 6628869 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7299. Min Range: -6.7299
Max Act: 6.4487. Min Act: -0.1700
Data Index: 1930656 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7299. Min Range: -6.7299
Max Act: 6.4487. Min Act: -0.1700
Data Index: 5271077 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7299. Min Range: -6.7299
Max Act: 6.3862. Min Act: -0.1700
Data Index: 5942055 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7299. Min Range: -6.7299
Max Act: 6.3862. Min Act: -0.1700
Data Index: 2319969 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7299. Min Range: -6.7299
Max Act: 6.3862. Min Act: -0.1700
Data Index: 4407851 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7299. Min Range: -6.7299
Max Act: 6.3549. Min Act: -0.1700
Data Index: 417785 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7299. Min Range: -6.7299
Max Act: 6.3549. Min Act: -0.1700
Data Index: 8341448 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7299. Min Range: -6.7299
Max Act: 6.2924. Min Act: -0.1700
Data Index: 4315731 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7299. Min Range: -6.7299
Max Act: 6.3549. Min Act: -0.1700
Data Index: 5837627 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7299. Min Range: -6.7299
Max Act: 6.3237. Min Act: -0.1700
Data Index: 8332609 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7299. Min Range: -6.7299
Max Act: 6.2924. Min Act: -0.1700
Data Index: 7639196 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7299. Min Range: -6.7299
Max Act: 6.2924. Min Act: -0.1700
Data Index: 6509337 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7299. Min Range: -6.7299
Max Act: 6.2612. Min Act: -0.1700
Data Index: 1491655 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7299. Min Range: -6.7299
Max Act: 6.2612. Min Act: -0.1700
Data Index: 2731188 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19