Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3536 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0640. Min Range: -5.0640
Max Act: 5.0640. Min Act: -0.1700
Data Index: 5739920 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0640. Min Range: -5.0640
Max Act: 4.9702. Min Act: -0.1700
Data Index: 4792514 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0640. Min Range: -5.0640
Max Act: 4.9702. Min Act: -0.1700
Data Index: 1673671 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0640. Min Range: -5.0640
Max Act: 4.9390. Min Act: -0.1700
Data Index: 7838206 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0640. Min Range: -5.0640
Max Act: 4.9077. Min Act: -0.1700
Data Index: 503437 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0640. Min Range: -5.0640
Max Act: 4.8765. Min Act: -0.1700
Data Index: 5778276 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0640. Min Range: -5.0640
Max Act: 4.8452. Min Act: -0.1700
Data Index: 4489092 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0640. Min Range: -5.0640
Max Act: 4.8765. Min Act: -0.1700
Data Index: 5348506 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0640. Min Range: -5.0640
Max Act: 4.8452. Min Act: -0.1700
Data Index: 6503021 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0640. Min Range: -5.0640
Max Act: 4.8140. Min Act: -0.1700
Data Index: 2507653 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0640. Min Range: -5.0640
Max Act: 4.8140. Min Act: -0.1700
Data Index: 3889465 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0640. Min Range: -5.0640
Max Act: 4.7827. Min Act: -0.1700
Data Index: 7766876 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0640. Min Range: -5.0640
Max Act: 4.7827. Min Act: -0.1700
Data Index: 751265 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0640. Min Range: -5.0640
Max Act: 4.8140. Min Act: -0.1700
Data Index: 700264 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0640. Min Range: -5.0640
Max Act: 4.7827. Min Act: -0.1700
Data Index: 1072384 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0640. Min Range: -5.0640
Max Act: 4.7827. Min Act: -0.1700
Data Index: 1739523 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0640. Min Range: -5.0640
Max Act: 4.7515. Min Act: -0.1700
Data Index: 4621775 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0640. Min Range: -5.0640
Max Act: 4.7515. Min Act: -0.1700
Data Index: 3713957 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0640. Min Range: -5.0640
Max Act: 4.7515. Min Act: -0.1700
Data Index: 5011517 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0640. Min Range: -5.0640
Max Act: 4.7515. Min Act: -0.1700
Data Index: 3756685 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19