Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1378 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3627. Min Range: -9.3627
Max Act: 9.3627. Min Act: -0.1700
Data Index: 2079175 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3627. Min Range: -9.3627
Max Act: 9.2377. Min Act: -0.1700
Data Index: 3158732 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3627. Min Range: -9.3627
Max Act: 9.2377. Min Act: -0.1700
Data Index: 5996704 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3627. Min Range: -9.3627
Max Act: 9.1752. Min Act: -0.1700
Data Index: 3039093 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3627. Min Range: -9.3627
Max Act: 9.1752. Min Act: -0.1700
Data Index: 8605809 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3627. Min Range: -9.3627
Max Act: 9.1752. Min Act: -0.1700
Data Index: 5024793 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3627. Min Range: -9.3627
Max Act: 9.1127. Min Act: -0.1700
Data Index: 4574833 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3627. Min Range: -9.3627
Max Act: 9.1752. Min Act: -0.1700
Data Index: 5994304 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3627. Min Range: -9.3627
Max Act: 9.1752. Min Act: -0.1700
Data Index: 1758216 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3627. Min Range: -9.3627
Max Act: 9.1752. Min Act: -0.1700
Data Index: 5870619 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3627. Min Range: -9.3627
Max Act: 9.1127. Min Act: -0.1700
Data Index: 5181857 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3627. Min Range: -9.3627
Max Act: 9.0502. Min Act: -0.1700
Data Index: 4294239 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3627. Min Range: -9.3627
Max Act: 9.1127. Min Act: -0.1700
Data Index: 5939674 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3627. Min Range: -9.3627
Max Act: 9.1127. Min Act: -0.1700
Data Index: 4164800 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3627. Min Range: -9.3627
Max Act: 9.1127. Min Act: -0.1700
Data Index: 5456734 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3627. Min Range: -9.3627
Max Act: 9.1127. Min Act: -0.1700
Data Index: 7462985 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3627. Min Range: -9.3627
Max Act: 9.1127. Min Act: -0.1700
Data Index: 5347449 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3627. Min Range: -9.3627
Max Act: 9.1127. Min Act: -0.1700
Data Index: 8155667 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3627. Min Range: -9.3627
Max Act: 9.1127. Min Act: -0.1700
Data Index: 3634315 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3627. Min Range: -9.3627
Max Act: 9.0502. Min Act: -0.1700
Data Index: 5142115 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19