Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3533 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4907. Min Range: -5.4907
Max Act: 5.4907. Min Act: -0.1700
Data Index: 2397578 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4907. Min Range: -5.4907
Max Act: 5.3970. Min Act: -0.1700
Data Index: 8481131 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4907. Min Range: -5.4907
Max Act: 5.1782. Min Act: -0.1700
Data Index: 317883 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4907. Min Range: -5.4907
Max Act: 5.1782. Min Act: -0.1700
Data Index: 8744710 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4907. Min Range: -5.4907
Max Act: 5.0845. Min Act: -0.1700
Data Index: 212666 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4907. Min Range: -5.4907
Max Act: 5.0532. Min Act: -0.1700
Data Index: 495564 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4907. Min Range: -5.4907
Max Act: 4.9282. Min Act: -0.1700
Data Index: 8795483 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4907. Min Range: -5.4907
Max Act: 4.8970. Min Act: -0.1700
Data Index: 1225859 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4907. Min Range: -5.4907
Max Act: 4.8970. Min Act: -0.1700
Data Index: 6205098 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4907. Min Range: -5.4907
Max Act: 4.8345. Min Act: -0.1700
Data Index: 8643296 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4907. Min Range: -5.4907
Max Act: 4.8345. Min Act: -0.1700
Data Index: 3495569 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4907. Min Range: -5.4907
Max Act: 4.8032. Min Act: -0.1700
Data Index: 7511709 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4907. Min Range: -5.4907
Max Act: 4.8032. Min Act: -0.1700
Data Index: 1227499 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4907. Min Range: -5.4907
Max Act: 4.7720. Min Act: -0.1700
Data Index: 5674395 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4907. Min Range: -5.4907
Max Act: 4.7720. Min Act: -0.1700
Data Index: 4795088 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4907. Min Range: -5.4907
Max Act: 4.7720. Min Act: -0.1700
Data Index: 7858637 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4907. Min Range: -5.4907
Max Act: 4.7407. Min Act: -0.1700
Data Index: 8260626 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4907. Min Range: -5.4907
Max Act: 4.6782. Min Act: -0.1700
Data Index: 1449982 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4907. Min Range: -5.4907
Max Act: 4.7095. Min Act: -0.1700
Data Index: 480589 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4907. Min Range: -5.4907
Max Act: 4.7095. Min Act: -0.1700
Data Index: 3964256 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19