Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 76 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1420. Min Range: -6.1420
Max Act: 6.1420. Min Act: -0.1700
Data Index: 6806554 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1420. Min Range: -6.1420
Max Act: 6.1420. Min Act: -0.1700
Data Index: 1164739 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1420. Min Range: -6.1420
Max Act: 6.0482. Min Act: -0.1700
Data Index: 8470178 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1420. Min Range: -6.1420
Max Act: 6.0170. Min Act: -0.1700
Data Index: 393826 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1420. Min Range: -6.1420
Max Act: 5.9857. Min Act: -0.1700
Data Index: 8720738 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1420. Min Range: -6.1420
Max Act: 5.9857. Min Act: -0.1700
Data Index: 1651777 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1420. Min Range: -6.1420
Max Act: 5.9232. Min Act: -0.1700
Data Index: 2755240 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1420. Min Range: -6.1420
Max Act: 5.8920. Min Act: -0.1700
Data Index: 5496491 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1420. Min Range: -6.1420
Max Act: 5.8920. Min Act: -0.1700
Data Index: 260643 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1420. Min Range: -6.1420
Max Act: 5.8920. Min Act: -0.1700
Data Index: 6291042 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1420. Min Range: -6.1420
Max Act: 5.8607. Min Act: -0.1700
Data Index: 8578190 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1420. Min Range: -6.1420
Max Act: 5.8607. Min Act: -0.1700
Data Index: 6015929 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1420. Min Range: -6.1420
Max Act: 5.8607. Min Act: -0.1700
Data Index: 4864678 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1420. Min Range: -6.1420
Max Act: 5.8295. Min Act: -0.1700
Data Index: 6688244 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1420. Min Range: -6.1420
Max Act: 5.7982. Min Act: -0.1700
Data Index: 1459887 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1420. Min Range: -6.1420
Max Act: 5.8295. Min Act: -0.1700
Data Index: 953632 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1420. Min Range: -6.1420
Max Act: 5.7982. Min Act: -0.1700
Data Index: 1077980 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1420. Min Range: -6.1420
Max Act: 5.7982. Min Act: -0.1700
Data Index: 7113804 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1420. Min Range: -6.1420
Max Act: 5.7670. Min Act: -0.1700
Data Index: 4989447 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1420. Min Range: -6.1420
Max Act: 5.7670. Min Act: -0.1700
Data Index: 2590338 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19