Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3450 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1076. Min Range: -6.1076
Max Act: 6.1076. Min Act: -0.1700
Data Index: 7549992 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.9826. Min Act: -0.1700
Data Index: 6886905 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.7638. Min Act: -0.1700
Data Index: 8624595 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.7638. Min Act: -0.1700
Data Index: 630779 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.7326. Min Act: -0.1700
Data Index: 543448 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.7326. Min Act: -0.1700
Data Index: 2011473 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.7326. Min Act: -0.1700
Data Index: 4371140 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.7326. Min Act: -0.1700
Data Index: 5936370 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.6076. Min Act: -0.1700
Data Index: 2491418 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.6076. Min Act: -0.1700
Data Index: 863247 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.6076. Min Act: -0.1700
Data Index: 6614638 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.5451. Min Act: -0.1700
Data Index: 6731477 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.5451. Min Act: -0.1700
Data Index: 5560350 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.5451. Min Act: -0.1700
Data Index: 6092044 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.5451. Min Act: -0.1700
Data Index: 4245647 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.5451. Min Act: -0.1700
Data Index: 5375987 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.5451. Min Act: -0.1700
Data Index: 3632706 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.5138. Min Act: -0.1700
Data Index: 840022 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.5138. Min Act: -0.1700
Data Index: 2485351 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1076. Min Range: -6.1076
Max Act: 5.5451. Min Act: -0.1700
Data Index: 1145719 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19