Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1813 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.3510. Min Range: -9.3510
Max Act: 9.3510. Min Act: -0.1700
Data Index: 2864696 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3510. Min Range: -9.3510
Max Act: 9.2885. Min Act: -0.1700
Data Index: 4492397 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3510. Min Range: -9.3510
Max Act: 9.2260. Min Act: -0.1700
Data Index: 6416961 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3510. Min Range: -9.3510
Max Act: 9.1010. Min Act: -0.1700
Data Index: 6687501 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3510. Min Range: -9.3510
Max Act: 9.1010. Min Act: -0.1700
Data Index: 7462550 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3510. Min Range: -9.3510
Max Act: 9.0385. Min Act: -0.1700
Data Index: 6191220 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3510. Min Range: -9.3510
Max Act: 8.9760. Min Act: -0.1700
Data Index: 3265716 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3510. Min Range: -9.3510
Max Act: 8.9760. Min Act: -0.1700
Data Index: 5397369 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3510. Min Range: -9.3510
Max Act: 8.8510. Min Act: -0.1700
Data Index: 4014322 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3510. Min Range: -9.3510
Max Act: 8.9135. Min Act: -0.1700
Data Index: 7798648 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3510. Min Range: -9.3510
Max Act: 8.8510. Min Act: -0.1700
Data Index: 8590096 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3510. Min Range: -9.3510
Max Act: 8.8510. Min Act: -0.1700
Data Index: 6633347 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3510. Min Range: -9.3510
Max Act: 8.8510. Min Act: -0.1700
Data Index: 3126719 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3510. Min Range: -9.3510
Max Act: 8.8510. Min Act: -0.1700
Data Index: 6057434 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3510. Min Range: -9.3510
Max Act: 8.9135. Min Act: -0.1700
Data Index: 5725852 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3510. Min Range: -9.3510
Max Act: 8.8510. Min Act: -0.1700
Data Index: 8208827 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3510. Min Range: -9.3510
Max Act: 8.7885. Min Act: -0.1700
Data Index: 6691807 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3510. Min Range: -9.3510
Max Act: 8.8510. Min Act: -0.1700
Data Index: 4654360 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3510. Min Range: -9.3510
Max Act: 8.7885. Min Act: -0.1700
Data Index: 3149875 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3510. Min Range: -9.3510
Max Act: 8.7885. Min Act: -0.1700
Data Index: 1543781 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19