Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3324 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8053. Min Range: -3.8053
Max Act: 3.8053. Min Act: -0.1700
Data Index: 8330990 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8053. Min Range: -3.8053
Max Act: 3.7584. Min Act: -0.1700
Data Index: 1100655 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8053. Min Range: -3.8053
Max Act: 3.7740. Min Act: -0.1700
Data Index: 8350220 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8053. Min Range: -3.8053
Max Act: 3.6958. Min Act: -0.1700
Data Index: 1526206 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8053. Min Range: -3.8053
Max Act: 3.6645. Min Act: -0.1700
Data Index: 6894687 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8053. Min Range: -3.8053
Max Act: 3.6645. Min Act: -0.1700
Data Index: 108183 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8053. Min Range: -3.8053
Max Act: 3.6489. Min Act: -0.1700
Data Index: 3949427 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8053. Min Range: -3.8053
Max Act: 3.6489. Min Act: -0.1700
Data Index: 850061 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8053. Min Range: -3.8053
Max Act: 3.6489. Min Act: -0.1700
Data Index: 3711883 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8053. Min Range: -3.8053
Max Act: 3.6489. Min Act: -0.1700
Data Index: 1866308 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8053. Min Range: -3.8053
Max Act: 3.6489. Min Act: -0.1700
Data Index: 244676 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8053. Min Range: -3.8053
Max Act: 3.6489. Min Act: -0.1700
Data Index: 3590129 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8053. Min Range: -3.8053
Max Act: 3.6489. Min Act: -0.1700
Data Index: 3449223 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8053. Min Range: -3.8053
Max Act: 3.6489. Min Act: -0.1700
Data Index: 1118372 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8053. Min Range: -3.8053
Max Act: 3.6489. Min Act: -0.1700
Data Index: 1583398 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8053. Min Range: -3.8053
Max Act: 3.6489. Min Act: -0.1700
Data Index: 4168071 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8053. Min Range: -3.8053
Max Act: 3.6489. Min Act: -0.1700
Data Index: 3488339 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8053. Min Range: -3.8053
Max Act: 3.6489. Min Act: -0.1700
Data Index: 1897776 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8053. Min Range: -3.8053
Max Act: 3.6489. Min Act: -0.1700
Data Index: 3306910 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8053. Min Range: -3.8053
Max Act: 3.6489. Min Act: -0.1700
Data Index: 305210 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19