Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2109 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.2009. Min Act: -0.1700
Data Index: 6974994 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.1222. Min Act: -0.1700
Data Index: 1538874 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.1380. Min Act: -0.1700
Data Index: 1852330 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.0592. Min Act: -0.1700
Data Index: 6318108 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.0749. Min Act: -0.1700
Data Index: 5688770 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.0434. Min Act: -0.1700
Data Index: 2807517 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.0434. Min Act: -0.1700
Data Index: 4434521 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.0276. Min Act: -0.1700
Data Index: 1653498 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.0118. Min Act: -0.1700
Data Index: 4166755 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.0276. Min Act: -0.1700
Data Index: 2714548 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2009. Min Range: -3.2009
Max Act: 2.9802. Min Act: -0.1700
Data Index: 1725287 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2009. Min Range: -3.2009
Max Act: 2.9960. Min Act: -0.1700
Data Index: 6985113 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2009. Min Range: -3.2009
Max Act: 2.9960. Min Act: -0.1700
Data Index: 1426558 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2009. Min Range: -3.2009
Max Act: 2.9960. Min Act: -0.1700
Data Index: 1236521 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2009. Min Range: -3.2009
Max Act: 2.9960. Min Act: -0.1700
Data Index: 3912355 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2009. Min Range: -3.2009
Max Act: 2.9644. Min Act: -0.1700
Data Index: 371111 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2009. Min Range: -3.2009
Max Act: 2.9485. Min Act: -0.1700
Data Index: 7610876 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2009. Min Range: -3.2009
Max Act: 2.9644. Min Act: -0.1700
Data Index: 4716086 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2009. Min Range: -3.2009
Max Act: 2.9644. Min Act: -0.1700
Data Index: 7466793 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2009. Min Range: -3.2009
Max Act: 2.9485. Min Act: -0.1700
Data Index: 5810184 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19