Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 355 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.7970. Min Act: -0.1698
Data Index: 8301328 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.7279. Min Act: -0.1699
Data Index: 8283573 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.7193. Min Act: -0.1693
Data Index: 5972024 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.7193. Min Act: -0.1700
Data Index: 1002064 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.7019. Min Act: -0.1647
Data Index: 3699434 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.6933. Min Act: -0.1699
Data Index: 6632719 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.6759. Min Act: -0.1700
Data Index: 7691857 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.6672. Min Act: -0.1700
Data Index: 601455 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.6672. Min Act: -0.1686
Data Index: 5915931 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.6759. Min Act: -0.1700
Data Index: 2378351 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.6585. Min Act: -0.1684
Data Index: 6948246 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.6585. Min Act: -0.1700
Data Index: 6632718 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.6411. Min Act: -0.1700
Data Index: 7565115 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.6498. Min Act: -0.1699
Data Index: 7456262 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.6585. Min Act: -0.1700
Data Index: 3453251 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.6411. Min Act: -0.1700
Data Index: 2591547 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.6498. Min Act: -0.1700
Data Index: 7363690 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.6411. Min Act: -0.1700
Data Index: 5935875 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.6411. Min Act: -0.1700
Data Index: 3225519 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.6411. Min Act: -0.1700
Data Index: 6328007 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19