Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 754 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0947. Min Range: -3.0947
Max Act: 3.0947. Min Act: -0.1700
Data Index: 4914977 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0947. Min Range: -3.0947
Max Act: 3.0158. Min Act: -0.1700
Data Index: 1915189 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0947. Min Range: -3.0947
Max Act: 2.9367. Min Act: -0.1700
Data Index: 5159953 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0947. Min Range: -3.0947
Max Act: 2.9209. Min Act: -0.1700
Data Index: 6981365 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0947. Min Range: -3.0947
Max Act: 2.9367. Min Act: -0.1700
Data Index: 1412188 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0947. Min Range: -3.0947
Max Act: 2.9050. Min Act: -0.1700
Data Index: 6540719 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0947. Min Range: -3.0947
Max Act: 2.9209. Min Act: -0.1700
Data Index: 6527454 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0947. Min Range: -3.0947
Max Act: 2.9050. Min Act: -0.1700
Data Index: 4549199 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0947. Min Range: -3.0947
Max Act: 2.8892. Min Act: -0.1700
Data Index: 2338933 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0947. Min Range: -3.0947
Max Act: 2.8733. Min Act: -0.1700
Data Index: 301079 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0947. Min Range: -3.0947
Max Act: 2.8892. Min Act: -0.1700
Data Index: 8493691 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0947. Min Range: -3.0947
Max Act: 2.8415. Min Act: -0.1700
Data Index: 1870264 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0947. Min Range: -3.0947
Max Act: 2.8733. Min Act: -0.1700
Data Index: 5426135 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0947. Min Range: -3.0947
Max Act: 2.8415. Min Act: -0.1700
Data Index: 5132578 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0947. Min Range: -3.0947
Max Act: 2.8574. Min Act: -0.1700
Data Index: 4212144 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0947. Min Range: -3.0947
Max Act: 2.8415. Min Act: -0.1700
Data Index: 5097314 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0947. Min Range: -3.0947
Max Act: 2.8256. Min Act: -0.1700
Data Index: 6726269 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0947. Min Range: -3.0947
Max Act: 2.8256. Min Act: -0.1700
Data Index: 2055523 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0947. Min Range: -3.0947
Max Act: 2.8097. Min Act: -0.1700
Data Index: 6394186 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0947. Min Range: -3.0947
Max Act: 2.8256. Min Act: -0.1700
Data Index: 2128476 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19