Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3727 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6068. Min Range: -5.6068
Max Act: 5.6068. Min Act: -0.1700
Data Index: 462400 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6068. Min Range: -5.6068
Max Act: 5.6068. Min Act: -0.1700
Data Index: 4905832 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6068. Min Range: -5.6068
Max Act: 5.5756. Min Act: -0.1700
Data Index: 2621638 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6068. Min Range: -5.6068
Max Act: 5.5443. Min Act: -0.1700
Data Index: 8504840 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6068. Min Range: -5.6068
Max Act: 5.5443. Min Act: -0.1700
Data Index: 5743569 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6068. Min Range: -5.6068
Max Act: 5.5131. Min Act: -0.1700
Data Index: 1516834 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6068. Min Range: -5.6068
Max Act: 5.5131. Min Act: -0.1700
Data Index: 7710000 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6068. Min Range: -5.6068
Max Act: 5.4818. Min Act: -0.1700
Data Index: 4873569 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6068. Min Range: -5.6068
Max Act: 5.5131. Min Act: -0.1700
Data Index: 2020248 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6068. Min Range: -5.6068
Max Act: 5.4818. Min Act: -0.1700
Data Index: 2242299 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6068. Min Range: -5.6068
Max Act: 5.4506. Min Act: -0.1700
Data Index: 6834590 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6068. Min Range: -5.6068
Max Act: 5.4193. Min Act: -0.1700
Data Index: 3861290 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6068. Min Range: -5.6068
Max Act: 5.4506. Min Act: -0.1700
Data Index: 5643167 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6068. Min Range: -5.6068
Max Act: 5.4193. Min Act: -0.1700
Data Index: 2688257 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6068. Min Range: -5.6068
Max Act: 5.3881. Min Act: -0.1700
Data Index: 3356329 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6068. Min Range: -5.6068
Max Act: 5.4506. Min Act: -0.1700
Data Index: 6979901 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6068. Min Range: -5.6068
Max Act: 5.4193. Min Act: -0.1700
Data Index: 7976302 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6068. Min Range: -5.6068
Max Act: 5.4506. Min Act: -0.1700
Data Index: 5938230 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6068. Min Range: -5.6068
Max Act: 5.3568. Min Act: -0.1700
Data Index: 2121842 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6068. Min Range: -5.6068
Max Act: 5.3568. Min Act: -0.1700
Data Index: 817414 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19