Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1819 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3014. Min Range: -5.3014
Max Act: 5.3014. Min Act: -0.1700
Data Index: 5892159 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3014. Min Range: -5.3014
Max Act: 5.3014. Min Act: -0.1700
Data Index: 2174007 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3014. Min Range: -5.3014
Max Act: 5.2389. Min Act: -0.1700
Data Index: 5741433 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3014. Min Range: -5.3014
Max Act: 5.2076. Min Act: -0.1700
Data Index: 8025316 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3014. Min Range: -5.3014
Max Act: 5.1764. Min Act: -0.1700
Data Index: 1865550 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3014. Min Range: -5.3014
Max Act: 5.1451. Min Act: -0.1700
Data Index: 7225624 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3014. Min Range: -5.3014
Max Act: 5.1139. Min Act: -0.1700
Data Index: 8278293 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3014. Min Range: -5.3014
Max Act: 5.0826. Min Act: -0.1700
Data Index: 6380837 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3014. Min Range: -5.3014
Max Act: 5.0514. Min Act: -0.1700
Data Index: 6693786 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3014. Min Range: -5.3014
Max Act: 5.0514. Min Act: -0.1700
Data Index: 6986888 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3014. Min Range: -5.3014
Max Act: 4.9889. Min Act: -0.1700
Data Index: 7376138 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3014. Min Range: -5.3014
Max Act: 5.0201. Min Act: -0.1700
Data Index: 6331527 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3014. Min Range: -5.3014
Max Act: 4.9889. Min Act: -0.1700
Data Index: 1164033 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3014. Min Range: -5.3014
Max Act: 4.8951. Min Act: -0.1700
Data Index: 6022849 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3014. Min Range: -5.3014
Max Act: 4.9264. Min Act: -0.1700
Data Index: 1546325 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3014. Min Range: -5.3014
Max Act: 4.8951. Min Act: -0.1700
Data Index: 5985428 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3014. Min Range: -5.3014
Max Act: 4.8951. Min Act: -0.1700
Data Index: 8233516 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3014. Min Range: -5.3014
Max Act: 4.8951. Min Act: -0.1700
Data Index: 8168784 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3014. Min Range: -5.3014
Max Act: 4.8639. Min Act: -0.1700
Data Index: 6084170 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3014. Min Range: -5.3014
Max Act: 4.8639. Min Act: -0.1700
Data Index: 2793201 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19