Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3146 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1434. Min Range: -4.1434
Max Act: 4.0497. Min Act: -0.1700
Data Index: 3314382 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1434. Min Range: -4.1434
Max Act: 4.1434. Min Act: -0.1700
Data Index: 6843588 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1434. Min Range: -4.1434
Max Act: 4.1122. Min Act: -0.1700
Data Index: 7687088 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1434. Min Range: -4.1434
Max Act: 4.1122. Min Act: -0.1700
Data Index: 2849988 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1434. Min Range: -4.1434
Max Act: 4.0497. Min Act: -0.1700
Data Index: 6687087 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1434. Min Range: -4.1434
Max Act: 4.0497. Min Act: -0.1700
Data Index: 7659032 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1434. Min Range: -4.1434
Max Act: 3.9872. Min Act: -0.1700
Data Index: 4479585 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1434. Min Range: -4.1434
Max Act: 3.9246. Min Act: -0.1700
Data Index: 367018 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1434. Min Range: -4.1434
Max Act: 3.9559. Min Act: -0.1700
Data Index: 7659025 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1434. Min Range: -4.1434
Max Act: 4.0184. Min Act: -0.1700
Data Index: 5801365 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1434. Min Range: -4.1434
Max Act: 3.9872. Min Act: -0.1700
Data Index: 7698403 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1434. Min Range: -4.1434
Max Act: 3.9246. Min Act: -0.1700
Data Index: 1268625 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1434. Min Range: -4.1434
Max Act: 3.9872. Min Act: -0.1700
Data Index: 8279306 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1434. Min Range: -4.1434
Max Act: 3.9246. Min Act: -0.1700
Data Index: 4613846 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1434. Min Range: -4.1434
Max Act: 3.9246. Min Act: -0.1700
Data Index: 2659928 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1434. Min Range: -4.1434
Max Act: 3.9246. Min Act: -0.1700
Data Index: 563712 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1434. Min Range: -4.1434
Max Act: 3.9246. Min Act: -0.1700
Data Index: 7205497 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1434. Min Range: -4.1434
Max Act: 3.9246. Min Act: -0.1700
Data Index: 5244479 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1434. Min Range: -4.1434
Max Act: 3.8934. Min Act: -0.1700
Data Index: 3025002 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1434. Min Range: -4.1434
Max Act: 3.8934. Min Act: -0.1700
Data Index: 4787323 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19