Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3278 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0434. Min Range: -8.0434
Max Act: 8.0434. Min Act: -0.1700
Data Index: 1215488 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0434. Min Range: -8.0434
Max Act: 7.8559. Min Act: -0.1700
Data Index: 1614527 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0434. Min Range: -8.0434
Max Act: 7.7934. Min Act: -0.1700
Data Index: 1346003 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0434. Min Range: -8.0434
Max Act: 7.7309. Min Act: -0.1700
Data Index: 3839358 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0434. Min Range: -8.0434
Max Act: 7.6997. Min Act: -0.1700
Data Index: 4777521 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0434. Min Range: -8.0434
Max Act: 7.6684. Min Act: -0.1700
Data Index: 3274022 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0434. Min Range: -8.0434
Max Act: 7.6372. Min Act: -0.1700
Data Index: 8539474 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0434. Min Range: -8.0434
Max Act: 7.6372. Min Act: -0.1700
Data Index: 1748209 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0434. Min Range: -8.0434
Max Act: 7.5747. Min Act: -0.1700
Data Index: 761806 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0434. Min Range: -8.0434
Max Act: 7.6059. Min Act: -0.1700
Data Index: 5207227 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0434. Min Range: -8.0434
Max Act: 7.5747. Min Act: -0.1700
Data Index: 3297802 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0434. Min Range: -8.0434
Max Act: 7.5747. Min Act: -0.1700
Data Index: 7422452 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0434. Min Range: -8.0434
Max Act: 7.5434. Min Act: -0.1700
Data Index: 8798046 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0434. Min Range: -8.0434
Max Act: 7.5434. Min Act: -0.1700
Data Index: 8726315 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0434. Min Range: -8.0434
Max Act: 7.5122. Min Act: -0.1700
Data Index: 8577870 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0434. Min Range: -8.0434
Max Act: 7.5122. Min Act: -0.1700
Data Index: 7568346 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0434. Min Range: -8.0434
Max Act: 7.4809. Min Act: -0.1700
Data Index: 5775567 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0434. Min Range: -8.0434
Max Act: 7.4809. Min Act: -0.1700
Data Index: 731400 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0434. Min Range: -8.0434
Max Act: 7.4497. Min Act: -0.1700
Data Index: 605090 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0434. Min Range: -8.0434
Max Act: 7.4184. Min Act: -0.1700
Data Index: 3862423 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19