Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4338 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.6521. Min Act: -0.1700
Data Index: 7654078 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.6208. Min Act: -0.1700
Data Index: 8130555 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.6364. Min Act: -0.1700
Data Index: 3150567 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.6208. Min Act: -0.1700
Data Index: 8419404 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.5425. Min Act: -0.1700
Data Index: 1066190 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.5582. Min Act: -0.1700
Data Index: 1150836 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.5425. Min Act: -0.1700
Data Index: 843159 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.5269. Min Act: -0.1700
Data Index: 8028037 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.5269. Min Act: -0.1700
Data Index: 3287965 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.5269. Min Act: -0.1700
Data Index: 853998 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.5269. Min Act: -0.1700
Data Index: 1816034 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.5112. Min Act: -0.1700
Data Index: 6857401 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.5112. Min Act: -0.1700
Data Index: 5175938 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.4955. Min Act: -0.1700
Data Index: 2388800 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.4799. Min Act: -0.1700
Data Index: 1309438 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.4642. Min Act: -0.1700
Data Index: 2832935 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.4955. Min Act: -0.1700
Data Index: 8348996 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.4799. Min Act: -0.1700
Data Index: 2184508 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.4642. Min Act: -0.1700
Data Index: 6388218 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.4799. Min Act: -0.1700
Data Index: 1799693 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19