Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4485 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1562. Min Range: -7.1562
Max Act: 7.1562. Min Act: -0.1700
Data Index: 8306865 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1562. Min Range: -7.1562
Max Act: 7.0312. Min Act: -0.1700
Data Index: 3717422 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1562. Min Range: -7.1562
Max Act: 7.0312. Min Act: -0.1700
Data Index: 4262386 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1562. Min Range: -7.1562
Max Act: 6.9687. Min Act: -0.1700
Data Index: 2384395 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1562. Min Range: -7.1562
Max Act: 6.9062. Min Act: -0.1700
Data Index: 1224563 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1562. Min Range: -7.1562
Max Act: 6.8750. Min Act: -0.1700
Data Index: 5988833 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1562. Min Range: -7.1562
Max Act: 6.8750. Min Act: -0.1700
Data Index: 5848207 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1562. Min Range: -7.1562
Max Act: 6.8125. Min Act: -0.1700
Data Index: 6451887 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1562. Min Range: -7.1562
Max Act: 6.8125. Min Act: -0.1700
Data Index: 4270303 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1562. Min Range: -7.1562
Max Act: 6.7500. Min Act: -0.1700
Data Index: 2523790 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1562. Min Range: -7.1562
Max Act: 6.7500. Min Act: -0.1700
Data Index: 6013856 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1562. Min Range: -7.1562
Max Act: 6.7500. Min Act: -0.1700
Data Index: 4206934 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1562. Min Range: -7.1562
Max Act: 6.7187. Min Act: -0.1700
Data Index: 4317572 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1562. Min Range: -7.1562
Max Act: 6.7187. Min Act: -0.1700
Data Index: 5232388 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1562. Min Range: -7.1562
Max Act: 6.7187. Min Act: -0.1700
Data Index: 5216068 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1562. Min Range: -7.1562
Max Act: 6.6875. Min Act: -0.1700
Data Index: 1644534 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1562. Min Range: -7.1562
Max Act: 6.6875. Min Act: -0.1700
Data Index: 8030870 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1562. Min Range: -7.1562
Max Act: 6.6875. Min Act: -0.1700
Data Index: 1740390 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1562. Min Range: -7.1562
Max Act: 6.6562. Min Act: -0.1700
Data Index: 3349183 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1562. Min Range: -7.1562
Max Act: 6.6562. Min Act: -0.1700
Data Index: 245498 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19