Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4413 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.5843. Min Act: -0.1700
Data Index: 4883612 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.4593. Min Act: -0.1700
Data Index: 2009914 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.4593. Min Act: -0.1700
Data Index: 3460684 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.4593. Min Act: -0.1700
Data Index: 2533282 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.3343. Min Act: -0.1700
Data Index: 1544874 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.2718. Min Act: -0.1700
Data Index: 8674680 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.2406. Min Act: -0.1700
Data Index: 8372373 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.2093. Min Act: -0.1700
Data Index: 5793647 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.2406. Min Act: -0.1700
Data Index: 928068 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.1781. Min Act: -0.1700
Data Index: 5968906 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.1781. Min Act: -0.1700
Data Index: 2597063 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.1781. Min Act: -0.1700
Data Index: 1118166 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.1468. Min Act: -0.1700
Data Index: 6149459 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.1781. Min Act: -0.1700
Data Index: 4990153 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.1781. Min Act: -0.1700
Data Index: 1206919 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.1468. Min Act: -0.1700
Data Index: 7075872 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.1781. Min Act: -0.1700
Data Index: 6734756 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.0843. Min Act: -0.1700
Data Index: 6329 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.1156. Min Act: -0.1700
Data Index: 1540064 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.1156. Min Act: -0.1700
Data Index: 7288397 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19