Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2034 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0833. Min Range: -10.0833
Max Act: 10.0833. Min Act: -0.1700
Data Index: 7600795 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0833. Min Range: -10.0833
Max Act: 9.4583. Min Act: -0.1700
Data Index: 5371016 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0833. Min Range: -10.0833
Max Act: 9.3958. Min Act: -0.1700
Data Index: 3680545 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0833. Min Range: -10.0833
Max Act: 9.3333. Min Act: -0.1700
Data Index: 3819914 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0833. Min Range: -10.0833
Max Act: 9.3333. Min Act: -0.1700
Data Index: 3120829 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0833. Min Range: -10.0833
Max Act: 9.3958. Min Act: -0.1700
Data Index: 4222821 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0833. Min Range: -10.0833
Max Act: 9.2708. Min Act: -0.1700
Data Index: 5678864 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0833. Min Range: -10.0833
Max Act: 9.2708. Min Act: -0.1700
Data Index: 6213288 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0833. Min Range: -10.0833
Max Act: 9.2083. Min Act: -0.1700
Data Index: 4108202 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0833. Min Range: -10.0833
Max Act: 9.2083. Min Act: -0.1700
Data Index: 4528641 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0833. Min Range: -10.0833
Max Act: 9.1458. Min Act: -0.1700
Data Index: 4528642 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0833. Min Range: -10.0833
Max Act: 9.1458. Min Act: -0.1700
Data Index: 4251150 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0833. Min Range: -10.0833
Max Act: 9.0833. Min Act: -0.1700
Data Index: 6793627 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0833. Min Range: -10.0833
Max Act: 9.0833. Min Act: -0.1700
Data Index: 7704616 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0833. Min Range: -10.0833
Max Act: 9.0833. Min Act: -0.1700
Data Index: 1186603 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0833. Min Range: -10.0833
Max Act: 9.0833. Min Act: -0.1700
Data Index: 5746352 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0833. Min Range: -10.0833
Max Act: 9.0208. Min Act: -0.1700
Data Index: 1668476 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0833. Min Range: -10.0833
Max Act: 8.9583. Min Act: -0.1700
Data Index: 3500821 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0833. Min Range: -10.0833
Max Act: 8.9583. Min Act: -0.1700
Data Index: 6116178 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0833. Min Range: -10.0833
Max Act: 8.9583. Min Act: -0.1700
Data Index: 1953385 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19