Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1917 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9331. Min Range: -5.9331
Max Act: 5.9331. Min Act: -0.1700
Data Index: 3528223 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9331. Min Range: -5.9331
Max Act: 5.9018. Min Act: -0.1700
Data Index: 3929271 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9331. Min Range: -5.9331
Max Act: 5.8706. Min Act: -0.1700
Data Index: 5177325 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9331. Min Range: -5.9331
Max Act: 5.9018. Min Act: -0.1700
Data Index: 220091 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9331. Min Range: -5.9331
Max Act: 5.8706. Min Act: -0.1700
Data Index: 465791 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9331. Min Range: -5.9331
Max Act: 5.8393. Min Act: -0.1700
Data Index: 7832089 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9331. Min Range: -5.9331
Max Act: 5.8393. Min Act: -0.1700
Data Index: 4603061 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9331. Min Range: -5.9331
Max Act: 5.8081. Min Act: -0.1700
Data Index: 6148433 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9331. Min Range: -5.9331
Max Act: 5.7768. Min Act: -0.1700
Data Index: 7137310 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9331. Min Range: -5.9331
Max Act: 5.7768. Min Act: -0.1700
Data Index: 4319649 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9331. Min Range: -5.9331
Max Act: 5.7143. Min Act: -0.1700
Data Index: 1392133 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9331. Min Range: -5.9331
Max Act: 5.7456. Min Act: -0.1700
Data Index: 2105515 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9331. Min Range: -5.9331
Max Act: 5.7143. Min Act: -0.1700
Data Index: 8747089 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9331. Min Range: -5.9331
Max Act: 5.6831. Min Act: -0.1700
Data Index: 3835837 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9331. Min Range: -5.9331
Max Act: 5.6831. Min Act: -0.1700
Data Index: 3435553 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9331. Min Range: -5.9331
Max Act: 5.6518. Min Act: -0.1700
Data Index: 320847 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9331. Min Range: -5.9331
Max Act: 5.6518. Min Act: -0.1700
Data Index: 7451044 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9331. Min Range: -5.9331
Max Act: 5.6206. Min Act: -0.1700
Data Index: 7427521 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9331. Min Range: -5.9331
Max Act: 5.5893. Min Act: -0.1700
Data Index: 4532297 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9331. Min Range: -5.9331
Max Act: 5.6518. Min Act: -0.1700
Data Index: 314137 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19