Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1695 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.8248. Min Range: -0.8248
Max Act: 0.8248. Min Act: -0.1700
Data Index: 6363648 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8248. Min Range: -0.8248
Max Act: 0.8164. Min Act: -0.1689
Data Index: 3171186 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8248. Min Range: -0.8248
Max Act: 0.7745. Min Act: -0.1700
Data Index: 8483594 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8248. Min Range: -0.8248
Max Act: 0.7662. Min Act: -0.1700
Data Index: 8120645 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8248. Min Range: -0.8248
Max Act: 0.7579. Min Act: -0.1697
Data Index: 4482636 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8248. Min Range: -0.8248
Max Act: 0.7413. Min Act: -0.1699
Data Index: 700024 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8248. Min Range: -0.8248
Max Act: 0.7249. Min Act: -0.1700
Data Index: 1261147 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8248. Min Range: -0.8248
Max Act: 0.7085. Min Act: -0.1700
Data Index: 7971266 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8248. Min Range: -0.8248
Max Act: 0.6921. Min Act: -0.1700
Data Index: 8763481 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8248. Min Range: -0.8248
Max Act: 0.6921. Min Act: -0.1700
Data Index: 5329585 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8248. Min Range: -0.8248
Max Act: 0.6840. Min Act: -0.1700
Data Index: 1121480 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8248. Min Range: -0.8248
Max Act: 0.6921. Min Act: -0.1699
Data Index: 3950948 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8248. Min Range: -0.8248
Max Act: 0.7003. Min Act: -0.1700
Data Index: 5772036 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8248. Min Range: -0.8248
Max Act: 0.6921. Min Act: -0.1699
Data Index: 5619161 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8248. Min Range: -0.8248
Max Act: 0.6759. Min Act: -0.1700
Data Index: 3932827 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8248. Min Range: -0.8248
Max Act: 0.6598. Min Act: -0.1697
Data Index: 6759721 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8248. Min Range: -0.8248
Max Act: 0.6598. Min Act: -0.1700
Data Index: 5159582 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8248. Min Range: -0.8248
Max Act: 0.6759. Min Act: -0.1700
Data Index: 4482635 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8248. Min Range: -0.8248
Max Act: 0.6678. Min Act: -0.1623
Data Index: 2409550 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8248. Min Range: -0.8248
Max Act: 0.6598. Min Act: -0.1700
Data Index: 8010302 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19