Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3109 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5583. Min Range: -5.5583
Max Act: 5.5583. Min Act: -0.1700
Data Index: 5105599 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5583. Min Range: -5.5583
Max Act: 5.5270. Min Act: -0.1700
Data Index: 1472671 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5583. Min Range: -5.5583
Max Act: 5.4958. Min Act: -0.1700
Data Index: 1853056 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5583. Min Range: -5.5583
Max Act: 5.4645. Min Act: -0.1700
Data Index: 3702896 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5583. Min Range: -5.5583
Max Act: 5.4333. Min Act: -0.1700
Data Index: 6151558 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5583. Min Range: -5.5583
Max Act: 5.4020. Min Act: -0.1700
Data Index: 650774 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5583. Min Range: -5.5583
Max Act: 5.4020. Min Act: -0.1700
Data Index: 6801727 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5583. Min Range: -5.5583
Max Act: 5.3708. Min Act: -0.1700
Data Index: 1026441 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5583. Min Range: -5.5583
Max Act: 5.3395. Min Act: -0.1700
Data Index: 3799458 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5583. Min Range: -5.5583
Max Act: 5.3083. Min Act: -0.1700
Data Index: 4307714 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5583. Min Range: -5.5583
Max Act: 5.2770. Min Act: -0.1700
Data Index: 4516779 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5583. Min Range: -5.5583
Max Act: 5.2770. Min Act: -0.1700
Data Index: 1706120 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5583. Min Range: -5.5583
Max Act: 5.2770. Min Act: -0.1700
Data Index: 4616669 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5583. Min Range: -5.5583
Max Act: 5.2458. Min Act: -0.1700
Data Index: 1954194 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5583. Min Range: -5.5583
Max Act: 5.2458. Min Act: -0.1700
Data Index: 3702902 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5583. Min Range: -5.5583
Max Act: 5.2145. Min Act: -0.1700
Data Index: 609928 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5583. Min Range: -5.5583
Max Act: 5.2145. Min Act: -0.1700
Data Index: 5008020 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5583. Min Range: -5.5583
Max Act: 5.2145. Min Act: -0.1700
Data Index: 3759054 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5583. Min Range: -5.5583
Max Act: 5.2145. Min Act: -0.1700
Data Index: 2156425 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5583. Min Range: -5.5583
Max Act: 5.1520. Min Act: -0.1700
Data Index: 2386832 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19