Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5330 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8650. Min Range: -5.8650
Max Act: 5.8650. Min Act: -0.1700
Data Index: 3308354 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8650. Min Range: -5.8650
Max Act: 5.5837. Min Act: -0.1700
Data Index: 5602126 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8650. Min Range: -5.8650
Max Act: 5.6150. Min Act: -0.1700
Data Index: 180572 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8650. Min Range: -5.8650
Max Act: 5.5525. Min Act: -0.1700
Data Index: 8585212 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8650. Min Range: -5.8650
Max Act: 5.4900. Min Act: -0.1700
Data Index: 3859679 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8650. Min Range: -5.8650
Max Act: 5.4900. Min Act: -0.1700
Data Index: 7935016 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8650. Min Range: -5.8650
Max Act: 5.4587. Min Act: -0.1700
Data Index: 4012844 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8650. Min Range: -5.8650
Max Act: 5.4587. Min Act: -0.1700
Data Index: 8578462 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8650. Min Range: -5.8650
Max Act: 5.4587. Min Act: -0.1700
Data Index: 401707 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8650. Min Range: -5.8650
Max Act: 5.4275. Min Act: -0.1700
Data Index: 5308538 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8650. Min Range: -5.8650
Max Act: 5.4275. Min Act: -0.1700
Data Index: 3125750 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8650. Min Range: -5.8650
Max Act: 5.4275. Min Act: -0.1700
Data Index: 1337573 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8650. Min Range: -5.8650
Max Act: 5.3962. Min Act: -0.1700
Data Index: 7044468 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8650. Min Range: -5.8650
Max Act: 5.3962. Min Act: -0.1700
Data Index: 5914161 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8650. Min Range: -5.8650
Max Act: 5.3962. Min Act: -0.1700
Data Index: 1801079 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8650. Min Range: -5.8650
Max Act: 5.3962. Min Act: -0.1700
Data Index: 5248163 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8650. Min Range: -5.8650
Max Act: 5.3650. Min Act: -0.1700
Data Index: 7077943 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8650. Min Range: -5.8650
Max Act: 5.3650. Min Act: -0.1700
Data Index: 5894641 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8650. Min Range: -5.8650
Max Act: 5.3650. Min Act: -0.1700
Data Index: 5434767 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8650. Min Range: -5.8650
Max Act: 5.3650. Min Act: -0.1700
Data Index: 2918634 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19