Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4605 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3436. Min Range: -6.3436
Max Act: 6.3436. Min Act: -0.1700
Data Index: 3910859 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3436. Min Range: -6.3436
Max Act: 6.3436. Min Act: -0.1700
Data Index: 2471614 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3436. Min Range: -6.3436
Max Act: 6.2811. Min Act: -0.1700
Data Index: 2811300 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3436. Min Range: -6.3436
Max Act: 6.2499. Min Act: -0.1700
Data Index: 6121554 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3436. Min Range: -6.3436
Max Act: 6.1561. Min Act: -0.1700
Data Index: 2471608 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3436. Min Range: -6.3436
Max Act: 6.1561. Min Act: -0.1700
Data Index: 1073311 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3436. Min Range: -6.3436
Max Act: 6.0936. Min Act: -0.1700
Data Index: 7297438 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3436. Min Range: -6.3436
Max Act: 5.9999. Min Act: -0.1700
Data Index: 4315973 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3436. Min Range: -6.3436
Max Act: 6.0311. Min Act: -0.1700
Data Index: 1810529 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3436. Min Range: -6.3436
Max Act: 5.9686. Min Act: -0.1700
Data Index: 5253138 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3436. Min Range: -6.3436
Max Act: 5.9374. Min Act: -0.1700
Data Index: 4900240 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3436. Min Range: -6.3436
Max Act: 5.9686. Min Act: -0.1700
Data Index: 2471610 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3436. Min Range: -6.3436
Max Act: 5.9374. Min Act: -0.1700
Data Index: 3704249 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3436. Min Range: -6.3436
Max Act: 5.9061. Min Act: -0.1700
Data Index: 1661087 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3436. Min Range: -6.3436
Max Act: 5.8749. Min Act: -0.1700
Data Index: 985588 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3436. Min Range: -6.3436
Max Act: 5.8749. Min Act: -0.1700
Data Index: 6340008 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3436. Min Range: -6.3436
Max Act: 5.8749. Min Act: -0.1700
Data Index: 5055937 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3436. Min Range: -6.3436
Max Act: 5.8436. Min Act: -0.1700
Data Index: 1425159 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3436. Min Range: -6.3436
Max Act: 5.8436. Min Act: -0.1700
Data Index: 26174 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3436. Min Range: -6.3436
Max Act: 5.8436. Min Act: -0.1700
Data Index: 3719539 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19