Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4866 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3060. Min Range: -2.3060
Max Act: 2.3060. Min Act: -0.1700
Data Index: 6818516 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3060. Min Range: -2.3060
Max Act: 2.2731. Min Act: -0.1700
Data Index: 1159332 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3060. Min Range: -2.3060
Max Act: 2.2235. Min Act: -0.1700
Data Index: 7937252 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3060. Min Range: -2.3060
Max Act: 2.2069. Min Act: -0.1700
Data Index: 4972390 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3060. Min Range: -2.3060
Max Act: 2.2069. Min Act: -0.1700
Data Index: 33621 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3060. Min Range: -2.3060
Max Act: 2.1737. Min Act: -0.1700
Data Index: 6374486 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3060. Min Range: -2.3060
Max Act: 2.1903. Min Act: -0.1700
Data Index: 4492553 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3060. Min Range: -2.3060
Max Act: 2.1737. Min Act: -0.1700
Data Index: 7644207 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3060. Min Range: -2.3060
Max Act: 2.1903. Min Act: -0.1700
Data Index: 1971156 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3060. Min Range: -2.3060
Max Act: 2.1571. Min Act: -0.1700
Data Index: 150835 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3060. Min Range: -2.3060
Max Act: 2.1571. Min Act: -0.1700
Data Index: 2637399 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3060. Min Range: -2.3060
Max Act: 2.1737. Min Act: -0.1700
Data Index: 4761197 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3060. Min Range: -2.3060
Max Act: 2.1571. Min Act: -0.1700
Data Index: 2985780 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3060. Min Range: -2.3060
Max Act: 2.1571. Min Act: -0.1700
Data Index: 8462029 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3060. Min Range: -2.3060
Max Act: 2.1404. Min Act: -0.1700
Data Index: 2238858 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3060. Min Range: -2.3060
Max Act: 2.1571. Min Act: -0.1700
Data Index: 6409326 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3060. Min Range: -2.3060
Max Act: 2.1571. Min Act: -0.1700
Data Index: 3319079 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3060. Min Range: -2.3060
Max Act: 2.1404. Min Act: -0.1700
Data Index: 5918609 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3060. Min Range: -2.3060
Max Act: 2.1237. Min Act: -0.1700
Data Index: 5490293 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3060. Min Range: -2.3060
Max Act: 2.1404. Min Act: -0.1700
Data Index: 8258174 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19