Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2027 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3201. Min Range: -6.3201
Max Act: 6.3201. Min Act: -0.1700
Data Index: 1134762 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3201. Min Range: -6.3201
Max Act: 6.1951. Min Act: -0.1700
Data Index: 5005151 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3201. Min Range: -6.3201
Max Act: 6.1639. Min Act: -0.1700
Data Index: 7844182 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3201. Min Range: -6.3201
Max Act: 6.1639. Min Act: -0.1700
Data Index: 7071408 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3201. Min Range: -6.3201
Max Act: 6.1326. Min Act: -0.1700
Data Index: 1931662 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3201. Min Range: -6.3201
Max Act: 6.1326. Min Act: -0.1700
Data Index: 1858223 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3201. Min Range: -6.3201
Max Act: 6.1014. Min Act: -0.1700
Data Index: 2963160 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3201. Min Range: -6.3201
Max Act: 6.1014. Min Act: -0.1700
Data Index: 8024664 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3201. Min Range: -6.3201
Max Act: 6.0701. Min Act: -0.1700
Data Index: 5248416 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3201. Min Range: -6.3201
Max Act: 6.0701. Min Act: -0.1700
Data Index: 1342294 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3201. Min Range: -6.3201
Max Act: 6.0701. Min Act: -0.1700
Data Index: 1342090 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3201. Min Range: -6.3201
Max Act: 6.0076. Min Act: -0.1700
Data Index: 6652833 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3201. Min Range: -6.3201
Max Act: 5.9764. Min Act: -0.1700
Data Index: 1948455 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3201. Min Range: -6.3201
Max Act: 5.9764. Min Act: -0.1700
Data Index: 8302464 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3201. Min Range: -6.3201
Max Act: 5.9451. Min Act: -0.1700
Data Index: 7350514 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3201. Min Range: -6.3201
Max Act: 5.9451. Min Act: -0.1700
Data Index: 6763893 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3201. Min Range: -6.3201
Max Act: 5.9451. Min Act: -0.1700
Data Index: 979349 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3201. Min Range: -6.3201
Max Act: 5.9451. Min Act: -0.1700
Data Index: 8470467 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3201. Min Range: -6.3201
Max Act: 5.8826. Min Act: -0.1700
Data Index: 6880692 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3201. Min Range: -6.3201
Max Act: 5.9139. Min Act: -0.1700
Data Index: 7823402 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19