Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 78 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4077. Min Range: -5.4077
Max Act: 5.4077. Min Act: -0.1700
Data Index: 5131414 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4077. Min Range: -5.4077
Max Act: 5.3765. Min Act: -0.1700
Data Index: 8180466 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4077. Min Range: -5.4077
Max Act: 5.3452. Min Act: -0.1700
Data Index: 3883789 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4077. Min Range: -5.4077
Max Act: 5.3452. Min Act: -0.1700
Data Index: 919775 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4077. Min Range: -5.4077
Max Act: 5.2202. Min Act: -0.1700
Data Index: 2492079 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4077. Min Range: -5.4077
Max Act: 5.2202. Min Act: -0.1700
Data Index: 3833366 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4077. Min Range: -5.4077
Max Act: 5.1577. Min Act: -0.1700
Data Index: 8661740 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4077. Min Range: -5.4077
Max Act: 5.1265. Min Act: -0.1700
Data Index: 7571339 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4077. Min Range: -5.4077
Max Act: 5.1265. Min Act: -0.1700
Data Index: 6636255 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4077. Min Range: -5.4077
Max Act: 5.0952. Min Act: -0.1700
Data Index: 4734967 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4077. Min Range: -5.4077
Max Act: 5.0952. Min Act: -0.1700
Data Index: 6321441 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4077. Min Range: -5.4077
Max Act: 5.0952. Min Act: -0.1700
Data Index: 2648412 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4077. Min Range: -5.4077
Max Act: 5.0640. Min Act: -0.1700
Data Index: 1043111 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4077. Min Range: -5.4077
Max Act: 5.0640. Min Act: -0.1700
Data Index: 3859201 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4077. Min Range: -5.4077
Max Act: 5.0640. Min Act: -0.1700
Data Index: 1458678 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4077. Min Range: -5.4077
Max Act: 5.0640. Min Act: -0.1700
Data Index: 689634 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4077. Min Range: -5.4077
Max Act: 5.0640. Min Act: -0.1700
Data Index: 6954324 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4077. Min Range: -5.4077
Max Act: 5.0327. Min Act: -0.1700
Data Index: 2008642 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4077. Min Range: -5.4077
Max Act: 5.0327. Min Act: -0.1700
Data Index: 6843623 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4077. Min Range: -5.4077
Max Act: 5.0327. Min Act: -0.1700
Data Index: 3434235 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19