Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1085 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0522. Min Range: -2.0522
Max Act: 2.0522. Min Act: -0.1700
Data Index: 6357953 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0522. Min Range: -2.0522
Max Act: 2.0354. Min Act: -0.1700
Data Index: 3479115 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0522. Min Range: -2.0522
Max Act: 2.0016. Min Act: -0.1700
Data Index: 571886 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0522. Min Range: -2.0522
Max Act: 1.9678. Min Act: -0.1700
Data Index: 4895102 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0522. Min Range: -2.0522
Max Act: 1.9508. Min Act: -0.1700
Data Index: 1132701 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0522. Min Range: -2.0522
Max Act: 1.9678. Min Act: -0.1700
Data Index: 7099644 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0522. Min Range: -2.0522
Max Act: 1.9508. Min Act: -0.1700
Data Index: 278839 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0522. Min Range: -2.0522
Max Act: 1.9508. Min Act: -0.1700
Data Index: 728203 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0522. Min Range: -2.0522
Max Act: 1.9508. Min Act: -0.1700
Data Index: 3638532 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0522. Min Range: -2.0522
Max Act: 1.9508. Min Act: -0.1700
Data Index: 1132705 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0522. Min Range: -2.0522
Max Act: 1.9338. Min Act: -0.1700
Data Index: 3578155 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0522. Min Range: -2.0522
Max Act: 1.9338. Min Act: -0.1700
Data Index: 6501902 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0522. Min Range: -2.0522
Max Act: 1.8998. Min Act: -0.1700
Data Index: 5326003 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0522. Min Range: -2.0522
Max Act: 1.8998. Min Act: -0.1700
Data Index: 3649154 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0522. Min Range: -2.0522
Max Act: 1.8998. Min Act: -0.1700
Data Index: 983661 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0522. Min Range: -2.0522
Max Act: 1.8827. Min Act: -0.1700
Data Index: 6565541 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0522. Min Range: -2.0522
Max Act: 1.8656. Min Act: -0.1700
Data Index: 1132706 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0522. Min Range: -2.0522
Max Act: 1.8827. Min Act: -0.1700
Data Index: 5238028 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0522. Min Range: -2.0522
Max Act: 1.8998. Min Act: -0.1700
Data Index: 7346104 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0522. Min Range: -2.0522
Max Act: 1.8827. Min Act: -0.1700
Data Index: 8673688 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19