Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1860 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8076. Min Range: -9.8076
Max Act: 9.8076. Min Act: -0.1700
Data Index: 3325847 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8076. Min Range: -9.8076
Max Act: 9.6201. Min Act: -0.1700
Data Index: 3935472 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8076. Min Range: -9.8076
Max Act: 9.6201. Min Act: -0.1700
Data Index: 2909661 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8076. Min Range: -9.8076
Max Act: 9.4951. Min Act: -0.1700
Data Index: 5298610 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8076. Min Range: -9.8076
Max Act: 9.4951. Min Act: -0.1700
Data Index: 3001974 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8076. Min Range: -9.8076
Max Act: 9.4951. Min Act: -0.1700
Data Index: 7468054 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8076. Min Range: -9.8076
Max Act: 9.4326. Min Act: -0.1700
Data Index: 424169 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8076. Min Range: -9.8076
Max Act: 9.3701. Min Act: -0.1700
Data Index: 819060 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8076. Min Range: -9.8076
Max Act: 9.3701. Min Act: -0.1700
Data Index: 3540827 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8076. Min Range: -9.8076
Max Act: 9.2451. Min Act: -0.1700
Data Index: 7742700 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8076. Min Range: -9.8076
Max Act: 9.2451. Min Act: -0.1700
Data Index: 197614 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8076. Min Range: -9.8076
Max Act: 9.1826. Min Act: -0.1700
Data Index: 7024853 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8076. Min Range: -9.8076
Max Act: 9.1201. Min Act: -0.1700
Data Index: 1015570 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8076. Min Range: -9.8076
Max Act: 9.1201. Min Act: -0.1700
Data Index: 1261710 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8076. Min Range: -9.8076
Max Act: 9.1201. Min Act: -0.1700
Data Index: 8466549 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8076. Min Range: -9.8076
Max Act: 9.1201. Min Act: -0.1700
Data Index: 32833 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8076. Min Range: -9.8076
Max Act: 8.9951. Min Act: -0.1700
Data Index: 2132233 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8076. Min Range: -9.8076
Max Act: 8.9951. Min Act: -0.1700
Data Index: 4711177 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8076. Min Range: -9.8076
Max Act: 8.9951. Min Act: -0.1700
Data Index: 2307316 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8076. Min Range: -9.8076
Max Act: 8.9326. Min Act: -0.1700
Data Index: 812436 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19