Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3233 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8314. Min Range: -4.8314
Max Act: 4.8314. Min Act: -0.1700
Data Index: 4432647 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8314. Min Range: -4.8314
Max Act: 4.8314. Min Act: -0.1700
Data Index: 1577862 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8314. Min Range: -4.8314
Max Act: 4.8002. Min Act: -0.1700
Data Index: 7017198 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8314. Min Range: -4.8314
Max Act: 4.7689. Min Act: -0.1700
Data Index: 197397 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8314. Min Range: -4.8314
Max Act: 4.7689. Min Act: -0.1700
Data Index: 2629730 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8314. Min Range: -4.8314
Max Act: 4.7689. Min Act: -0.1700
Data Index: 5203394 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8314. Min Range: -4.8314
Max Act: 4.7377. Min Act: -0.1700
Data Index: 1856174 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8314. Min Range: -4.8314
Max Act: 4.7377. Min Act: -0.1700
Data Index: 8304711 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8314. Min Range: -4.8314
Max Act: 4.7064. Min Act: -0.1700
Data Index: 5403858 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8314. Min Range: -4.8314
Max Act: 4.6752. Min Act: -0.1700
Data Index: 6630748 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8314. Min Range: -4.8314
Max Act: 4.6752. Min Act: -0.1700
Data Index: 3164566 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8314. Min Range: -4.8314
Max Act: 4.7064. Min Act: -0.1700
Data Index: 4160357 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8314. Min Range: -4.8314
Max Act: 4.6752. Min Act: -0.1700
Data Index: 2780225 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8314. Min Range: -4.8314
Max Act: 4.6439. Min Act: -0.1700
Data Index: 3973351 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8314. Min Range: -4.8314
Max Act: 4.6439. Min Act: -0.1700
Data Index: 1468958 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8314. Min Range: -4.8314
Max Act: 4.6127. Min Act: -0.1700
Data Index: 6065195 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8314. Min Range: -4.8314
Max Act: 4.6439. Min Act: -0.1700
Data Index: 5946312 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8314. Min Range: -4.8314
Max Act: 4.6439. Min Act: -0.1700
Data Index: 1760569 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8314. Min Range: -4.8314
Max Act: 4.6439. Min Act: -0.1700
Data Index: 4415952 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8314. Min Range: -4.8314
Max Act: 4.6439. Min Act: -0.1700
Data Index: 339939 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19