Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4883 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4911. Min Range: -6.4911
Max Act: 6.4911. Min Act: -0.1700
Data Index: 8195564 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4911. Min Range: -6.4911
Max Act: 6.4286. Min Act: -0.1700
Data Index: 3954664 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4911. Min Range: -6.4911
Max Act: 6.3349. Min Act: -0.1700
Data Index: 3735482 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4911. Min Range: -6.4911
Max Act: 6.3349. Min Act: -0.1700
Data Index: 4467612 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4911. Min Range: -6.4911
Max Act: 6.3349. Min Act: -0.1700
Data Index: 1638039 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4911. Min Range: -6.4911
Max Act: 6.3036. Min Act: -0.1700
Data Index: 3559016 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4911. Min Range: -6.4911
Max Act: 6.3036. Min Act: -0.1700
Data Index: 1460169 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4911. Min Range: -6.4911
Max Act: 6.2411. Min Act: -0.1700
Data Index: 3446162 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4911. Min Range: -6.4911
Max Act: 6.2724. Min Act: -0.1700
Data Index: 2192983 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4911. Min Range: -6.4911
Max Act: 6.3036. Min Act: -0.1700
Data Index: 7551585 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4911. Min Range: -6.4911
Max Act: 6.2724. Min Act: -0.1700
Data Index: 7551587 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4911. Min Range: -6.4911
Max Act: 6.2411. Min Act: -0.1700
Data Index: 2507398 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4911. Min Range: -6.4911
Max Act: 6.2411. Min Act: -0.1700
Data Index: 3060902 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4911. Min Range: -6.4911
Max Act: 6.2724. Min Act: -0.1700
Data Index: 1197466 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4911. Min Range: -6.4911
Max Act: 6.2099. Min Act: -0.1700
Data Index: 1332568 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4911. Min Range: -6.4911
Max Act: 6.2099. Min Act: -0.1700
Data Index: 178660 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4911. Min Range: -6.4911
Max Act: 6.2099. Min Act: -0.1700
Data Index: 1425210 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4911. Min Range: -6.4911
Max Act: 6.2099. Min Act: -0.1700
Data Index: 5112870 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4911. Min Range: -6.4911
Max Act: 6.2099. Min Act: -0.1700
Data Index: 3526427 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4911. Min Range: -6.4911
Max Act: 6.1786. Min Act: -0.1700
Data Index: 1828659 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19