Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2657 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9793. Min Range: -1.9793
Max Act: 1.9793. Min Act: -0.1698
Data Index: 2126001 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9793. Min Range: -1.9793
Max Act: 1.9283. Min Act: -0.1700
Data Index: 1802879 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9793. Min Range: -1.9793
Max Act: 1.9113. Min Act: -0.1700
Data Index: 8191101 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9793. Min Range: -1.9793
Max Act: 1.9283. Min Act: -0.1700
Data Index: 4399003 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9793. Min Range: -1.9793
Max Act: 1.9283. Min Act: -0.1700
Data Index: 2126000 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9793. Min Range: -1.9793
Max Act: 1.9113. Min Act: -0.1700
Data Index: 5718343 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9793. Min Range: -1.9793
Max Act: 1.8943. Min Act: -0.1700
Data Index: 3737296 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9793. Min Range: -1.9793
Max Act: 1.8772. Min Act: -0.1700
Data Index: 6529584 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9793. Min Range: -1.9793
Max Act: 1.8772. Min Act: -0.1700
Data Index: 8069583 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9793. Min Range: -1.9793
Max Act: 1.8601. Min Act: -0.1700
Data Index: 6309528 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9793. Min Range: -1.9793
Max Act: 1.8601. Min Act: -0.1700
Data Index: 2625343 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9793. Min Range: -1.9793
Max Act: 1.8430. Min Act: -0.1700
Data Index: 3392658 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9793. Min Range: -1.9793
Max Act: 1.8430. Min Act: -0.1700
Data Index: 7933203 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9793. Min Range: -1.9793
Max Act: 1.8430. Min Act: -0.1699
Data Index: 807932 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9793. Min Range: -1.9793
Max Act: 1.8430. Min Act: -0.1700
Data Index: 3704932 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9793. Min Range: -1.9793
Max Act: 1.8430. Min Act: -0.1700
Data Index: 7673800 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9793. Min Range: -1.9793
Max Act: 1.8344. Min Act: -0.1700
Data Index: 5279584 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9793. Min Range: -1.9793
Max Act: 1.8258. Min Act: -0.1698
Data Index: 6450109 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9793. Min Range: -1.9793
Max Act: 1.8086. Min Act: -0.1700
Data Index: 4493249 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9793. Min Range: -1.9793
Max Act: 1.8258. Min Act: -0.1700
Data Index: 2992476 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19