Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2147 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4246. Min Range: -4.4246
Max Act: 4.4246. Min Act: -0.1700
Data Index: 1141034 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4246. Min Range: -4.4246
Max Act: 4.4246. Min Act: -0.1700
Data Index: 7709242 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4246. Min Range: -4.4246
Max Act: 4.3933. Min Act: -0.1700
Data Index: 4250033 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4246. Min Range: -4.4246
Max Act: 4.3933. Min Act: -0.1700
Data Index: 5070056 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4246. Min Range: -4.4246
Max Act: 4.3933. Min Act: -0.1700
Data Index: 2138882 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4246. Min Range: -4.4246
Max Act: 4.3933. Min Act: -0.1700
Data Index: 3522418 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4246. Min Range: -4.4246
Max Act: 4.3933. Min Act: -0.1700
Data Index: 7349342 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4246. Min Range: -4.4246
Max Act: 4.3933. Min Act: -0.1700
Data Index: 6254353 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4246. Min Range: -4.4246
Max Act: 4.3933. Min Act: -0.1700
Data Index: 6008188 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4246. Min Range: -4.4246
Max Act: 4.3933. Min Act: -0.1700
Data Index: 1684649 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4246. Min Range: -4.4246
Max Act: 4.3933. Min Act: -0.1700
Data Index: 5955114 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4246. Min Range: -4.4246
Max Act: 4.3621. Min Act: -0.1700
Data Index: 3498542 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4246. Min Range: -4.4246
Max Act: 4.3621. Min Act: -0.1700
Data Index: 5606709 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4246. Min Range: -4.4246
Max Act: 4.3621. Min Act: -0.1700
Data Index: 2974922 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4246. Min Range: -4.4246
Max Act: 4.3621. Min Act: -0.1700
Data Index: 8215998 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4246. Min Range: -4.4246
Max Act: 4.3621. Min Act: -0.1700
Data Index: 2855261 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4246. Min Range: -4.4246
Max Act: 4.3621. Min Act: -0.1700
Data Index: 569515 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4246. Min Range: -4.4246
Max Act: 4.3621. Min Act: -0.1700
Data Index: 4177114 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4246. Min Range: -4.4246
Max Act: 4.3621. Min Act: -0.1700
Data Index: 1174154 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4246. Min Range: -4.4246
Max Act: 4.3308. Min Act: -0.1700
Data Index: 2188071 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19