Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4265 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8562. Min Range: -1.8562
Max Act: 1.8562. Min Act: -0.1699
Data Index: 8610425 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8562. Min Range: -1.8562
Max Act: 1.8390. Min Act: -0.1699
Data Index: 6187340 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8562. Min Range: -1.8562
Max Act: 1.7702. Min Act: -0.1700
Data Index: 1723384 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8562. Min Range: -1.8562
Max Act: 1.7530. Min Act: -0.1700
Data Index: 3959413 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8562. Min Range: -1.8562
Max Act: 1.6837. Min Act: -0.1695
Data Index: 8587176 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8562. Min Range: -1.8562
Max Act: 1.6663. Min Act: -0.1700
Data Index: 17961 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8562. Min Range: -1.8562
Max Act: 1.6489. Min Act: -0.1699
Data Index: 3959421 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8562. Min Range: -1.8562
Max Act: 1.6489. Min Act: -0.1700
Data Index: 17962 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8562. Min Range: -1.8562
Max Act: 1.6489. Min Act: -0.1700
Data Index: 2626227 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8562. Min Range: -1.8562
Max Act: 1.6315. Min Act: -0.1700
Data Index: 3959437 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8562. Min Range: -1.8562
Max Act: 1.6315. Min Act: -0.1700
Data Index: 6097216 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8562. Min Range: -1.8562
Max Act: 1.6141. Min Act: -0.1700
Data Index: 2709083 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8562. Min Range: -1.8562
Max Act: 1.6141. Min Act: -0.1700
Data Index: 6857039 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8562. Min Range: -1.8562
Max Act: 1.6141. Min Act: -0.1700
Data Index: 7721690 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8562. Min Range: -1.8562
Max Act: 1.6141. Min Act: -0.1700
Data Index: 5158849 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8562. Min Range: -1.8562
Max Act: 1.6141. Min Act: -0.1700
Data Index: 5928181 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8562. Min Range: -1.8562
Max Act: 1.5966. Min Act: -0.1700
Data Index: 3626988 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8562. Min Range: -1.8562
Max Act: 1.5791. Min Act: -0.1690
Data Index: 5928180 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8562. Min Range: -1.8562
Max Act: 1.5966. Min Act: -0.1700
Data Index: 17960 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8562. Min Range: -1.8562
Max Act: 1.5966. Min Act: -0.1700
Data Index: 1218370 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19