Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 421 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2451. Min Range: -5.2451
Max Act: 5.2451. Min Act: -0.1700
Data Index: 6498133 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2451. Min Range: -5.2451
Max Act: 5.1826. Min Act: -0.1700
Data Index: 3226766 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2451. Min Range: -5.2451
Max Act: 4.9639. Min Act: -0.1700
Data Index: 5679952 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2451. Min Range: -5.2451
Max Act: 4.9326. Min Act: -0.1700
Data Index: 5679953 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2451. Min Range: -5.2451
Max Act: 4.9326. Min Act: -0.1700
Data Index: 1192871 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2451. Min Range: -5.2451
Max Act: 4.9014. Min Act: -0.1700
Data Index: 126627 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2451. Min Range: -5.2451
Max Act: 4.9014. Min Act: -0.1700
Data Index: 207423 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2451. Min Range: -5.2451
Max Act: 4.9014. Min Act: -0.1700
Data Index: 761275 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2451. Min Range: -5.2451
Max Act: 4.9014. Min Act: -0.1700
Data Index: 1854760 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2451. Min Range: -5.2451
Max Act: 4.9014. Min Act: -0.1700
Data Index: 754677 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2451. Min Range: -5.2451
Max Act: 4.9014. Min Act: -0.1700
Data Index: 2348197 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2451. Min Range: -5.2451
Max Act: 4.9014. Min Act: -0.1700
Data Index: 1485192 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2451. Min Range: -5.2451
Max Act: 4.9014. Min Act: -0.1700
Data Index: 1634332 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2451. Min Range: -5.2451
Max Act: 4.9014. Min Act: -0.1700
Data Index: 302387 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2451. Min Range: -5.2451
Max Act: 4.9014. Min Act: -0.1700
Data Index: 259607 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2451. Min Range: -5.2451
Max Act: 4.9014. Min Act: -0.1700
Data Index: 846097 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2451. Min Range: -5.2451
Max Act: 4.9014. Min Act: -0.1700
Data Index: 544044 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2451. Min Range: -5.2451
Max Act: 4.9014. Min Act: -0.1700
Data Index: 1955434 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2451. Min Range: -5.2451
Max Act: 4.9014. Min Act: -0.1700
Data Index: 1226342 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2451. Min Range: -5.2451
Max Act: 4.9014. Min Act: -0.1700
Data Index: 797050 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19