Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3729 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4349. Min Range: -5.4349
Max Act: 5.4037. Min Act: -0.1700
Data Index: 8172994 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4349. Min Range: -5.4349
Max Act: 5.4349. Min Act: -0.1700
Data Index: 3272522 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4349. Min Range: -5.4349
Max Act: 5.3412. Min Act: -0.1700
Data Index: 3721582 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4349. Min Range: -5.4349
Max Act: 5.2162. Min Act: -0.1700
Data Index: 8603035 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4349. Min Range: -5.4349
Max Act: 5.1849. Min Act: -0.1700
Data Index: 8633055 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4349. Min Range: -5.4349
Max Act: 5.1537. Min Act: -0.1700
Data Index: 1580968 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4349. Min Range: -5.4349
Max Act: 5.1537. Min Act: -0.1700
Data Index: 7029201 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4349. Min Range: -5.4349
Max Act: 5.1224. Min Act: -0.1700
Data Index: 4245237 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4349. Min Range: -5.4349
Max Act: 5.1224. Min Act: -0.1700
Data Index: 59579 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4349. Min Range: -5.4349
Max Act: 5.1224. Min Act: -0.1700
Data Index: 4112734 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4349. Min Range: -5.4349
Max Act: 5.1224. Min Act: -0.1700
Data Index: 4004492 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4349. Min Range: -5.4349
Max Act: 5.0912. Min Act: -0.1700
Data Index: 1463190 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4349. Min Range: -5.4349
Max Act: 5.0287. Min Act: -0.1700
Data Index: 3325849 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4349. Min Range: -5.4349
Max Act: 5.0287. Min Act: -0.1700
Data Index: 2690290 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4349. Min Range: -5.4349
Max Act: 4.9974. Min Act: -0.1700
Data Index: 224987 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4349. Min Range: -5.4349
Max Act: 4.9974. Min Act: -0.1700
Data Index: 2044959 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4349. Min Range: -5.4349
Max Act: 4.9661. Min Act: -0.1700
Data Index: 8830830 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4349. Min Range: -5.4349
Max Act: 4.9661. Min Act: -0.1700
Data Index: 8655492 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4349. Min Range: -5.4349
Max Act: 4.9661. Min Act: -0.1700
Data Index: 4886704 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4349. Min Range: -5.4349
Max Act: 4.9661. Min Act: -0.1700
Data Index: 2183075 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19