Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5287 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.7903. Min Act: -0.1700
Data Index: 2342311 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.7590. Min Act: -0.1700
Data Index: 1060843 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.7590. Min Act: -0.1700
Data Index: 7595289 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.7590. Min Act: -0.1700
Data Index: 7214753 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.7278. Min Act: -0.1700
Data Index: 7475830 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.7278. Min Act: -0.1700
Data Index: 7394613 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.7278. Min Act: -0.1700
Data Index: 315437 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.6965. Min Act: -0.1700
Data Index: 7334214 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.7278. Min Act: -0.1700
Data Index: 6778311 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.7278. Min Act: -0.1700
Data Index: 2145840 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.7278. Min Act: -0.1700
Data Index: 5443331 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.6965. Min Act: -0.1700
Data Index: 8330328 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.7278. Min Act: -0.1700
Data Index: 8131329 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.7278. Min Act: -0.1700
Data Index: 3011660 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.6965. Min Act: -0.1700
Data Index: 5532288 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.6965. Min Act: -0.1700
Data Index: 5704703 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.6653. Min Act: -0.1700
Data Index: 6286121 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.6965. Min Act: -0.1700
Data Index: 4922324 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.6965. Min Act: -0.1700
Data Index: 2777881 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.6965. Min Act: -0.1700
Data Index: 2933998 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19