Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2459 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9691. Min Range: -2.9691
Max Act: 2.9691. Min Act: -0.1700
Data Index: 7157336 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9691. Min Range: -2.9691
Max Act: 2.9216. Min Act: -0.1700
Data Index: 3650820 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9691. Min Range: -2.9691
Max Act: 2.8740. Min Act: -0.1700
Data Index: 3010301 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9691. Min Range: -2.9691
Max Act: 2.8423. Min Act: -0.1700
Data Index: 3869915 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9691. Min Range: -2.9691
Max Act: 2.8423. Min Act: -0.1700
Data Index: 8641590 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9691. Min Range: -2.9691
Max Act: 2.8423. Min Act: -0.1700
Data Index: 2794491 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9691. Min Range: -2.9691
Max Act: 2.8423. Min Act: -0.1700
Data Index: 7800830 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9691. Min Range: -2.9691
Max Act: 2.8582. Min Act: -0.1700
Data Index: 5745132 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9691. Min Range: -2.9691
Max Act: 2.8423. Min Act: -0.1700
Data Index: 173687 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9691. Min Range: -2.9691
Max Act: 2.7945. Min Act: -0.1700
Data Index: 3247122 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9691. Min Range: -2.9691
Max Act: 2.7945. Min Act: -0.1700
Data Index: 2441977 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9691. Min Range: -2.9691
Max Act: 2.7786. Min Act: -0.1700
Data Index: 1261961 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9691. Min Range: -2.9691
Max Act: 2.7467. Min Act: -0.1700
Data Index: 5485043 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9691. Min Range: -2.9691
Max Act: 2.7786. Min Act: -0.1700
Data Index: 1482277 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9691. Min Range: -2.9691
Max Act: 2.7467. Min Act: -0.1700
Data Index: 1532887 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9691. Min Range: -2.9691
Max Act: 2.7467. Min Act: -0.1700
Data Index: 4379076 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9691. Min Range: -2.9691
Max Act: 2.7467. Min Act: -0.1700
Data Index: 1171472 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9691. Min Range: -2.9691
Max Act: 2.7467. Min Act: -0.1700
Data Index: 4813741 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9691. Min Range: -2.9691
Max Act: 2.7467. Min Act: -0.1700
Data Index: 3235962 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9691. Min Range: -2.9691
Max Act: 2.7307. Min Act: -0.1700
Data Index: 8181488 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19