Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3050 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9404. Min Range: -3.9404
Max Act: 3.9404. Min Act: -0.1700
Data Index: 5713428 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9404. Min Range: -3.9404
Max Act: 3.8778. Min Act: -0.1700
Data Index: 825303 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9404. Min Range: -3.9404
Max Act: 3.8622. Min Act: -0.1700
Data Index: 1223730 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9404. Min Range: -3.9404
Max Act: 3.8153. Min Act: -0.1700
Data Index: 6314708 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9404. Min Range: -3.9404
Max Act: 3.7997. Min Act: -0.1700
Data Index: 580966 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9404. Min Range: -3.9404
Max Act: 3.8153. Min Act: -0.1700
Data Index: 5023674 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9404. Min Range: -3.9404
Max Act: 3.7997. Min Act: -0.1700
Data Index: 2583785 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9404. Min Range: -3.9404
Max Act: 3.7997. Min Act: -0.1700
Data Index: 7508042 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9404. Min Range: -3.9404
Max Act: 3.8153. Min Act: -0.1700
Data Index: 4534146 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9404. Min Range: -3.9404
Max Act: 3.7997. Min Act: -0.1700
Data Index: 2925946 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9404. Min Range: -3.9404
Max Act: 3.7840. Min Act: -0.1700
Data Index: 2087546 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9404. Min Range: -3.9404
Max Act: 3.7684. Min Act: -0.1700
Data Index: 4605466 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9404. Min Range: -3.9404
Max Act: 3.7528. Min Act: -0.1700
Data Index: 8827601 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9404. Min Range: -3.9404
Max Act: 3.7371. Min Act: -0.1700
Data Index: 4545745 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9404. Min Range: -3.9404
Max Act: 3.7215. Min Act: -0.1700
Data Index: 2087549 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9404. Min Range: -3.9404
Max Act: 3.7215. Min Act: -0.1700
Data Index: 5544792 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9404. Min Range: -3.9404
Max Act: 3.7371. Min Act: -0.1700
Data Index: 3625517 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9404. Min Range: -3.9404
Max Act: 3.7058. Min Act: -0.1700
Data Index: 4454957 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9404. Min Range: -3.9404
Max Act: 3.7058. Min Act: -0.1700
Data Index: 1922749 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9404. Min Range: -3.9404
Max Act: 3.7215. Min Act: -0.1700
Data Index: 2925954 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19