Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3033 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2552. Min Range: -6.2552
Max Act: 6.2552. Min Act: -0.1700
Data Index: 1487848 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2552. Min Range: -6.2552
Max Act: 6.1927. Min Act: -0.1700
Data Index: 7961047 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2552. Min Range: -6.2552
Max Act: 6.0052. Min Act: -0.1700
Data Index: 567132 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2552. Min Range: -6.2552
Max Act: 5.9427. Min Act: -0.1700
Data Index: 7383358 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2552. Min Range: -6.2552
Max Act: 5.9115. Min Act: -0.1700
Data Index: 7413276 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2552. Min Range: -6.2552
Max Act: 5.8802. Min Act: -0.1700
Data Index: 7676918 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2552. Min Range: -6.2552
Max Act: 5.9115. Min Act: -0.1700
Data Index: 1084532 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2552. Min Range: -6.2552
Max Act: 5.8802. Min Act: -0.1700
Data Index: 4549632 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2552. Min Range: -6.2552
Max Act: 5.8490. Min Act: -0.1700
Data Index: 1040914 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2552. Min Range: -6.2552
Max Act: 5.8490. Min Act: -0.1700
Data Index: 4973776 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2552. Min Range: -6.2552
Max Act: 5.8177. Min Act: -0.1700
Data Index: 6973996 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2552. Min Range: -6.2552
Max Act: 5.8177. Min Act: -0.1700
Data Index: 1485016 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2552. Min Range: -6.2552
Max Act: 5.8177. Min Act: -0.1700
Data Index: 6772445 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2552. Min Range: -6.2552
Max Act: 5.8177. Min Act: -0.1700
Data Index: 126480 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2552. Min Range: -6.2552
Max Act: 5.7865. Min Act: -0.1700
Data Index: 7720432 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2552. Min Range: -6.2552
Max Act: 5.7865. Min Act: -0.1700
Data Index: 2616768 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2552. Min Range: -6.2552
Max Act: 5.7865. Min Act: -0.1700
Data Index: 2616767 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2552. Min Range: -6.2552
Max Act: 5.7865. Min Act: -0.1700
Data Index: 6363166 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2552. Min Range: -6.2552
Max Act: 5.7865. Min Act: -0.1700
Data Index: 2152003 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2552. Min Range: -6.2552
Max Act: 5.7865. Min Act: -0.1700
Data Index: 2434397 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19