Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1836 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2350. Min Range: -5.2350
Max Act: 5.2350. Min Act: -0.1700
Data Index: 7281051 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2350. Min Range: -5.2350
Max Act: 5.0162. Min Act: -0.1700
Data Index: 579565 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2350. Min Range: -5.2350
Max Act: 4.9850. Min Act: -0.1700
Data Index: 4960410 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2350. Min Range: -5.2350
Max Act: 4.9537. Min Act: -0.1700
Data Index: 2141241 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2350. Min Range: -5.2350
Max Act: 4.9537. Min Act: -0.1700
Data Index: 6299739 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2350. Min Range: -5.2350
Max Act: 4.9225. Min Act: -0.1700
Data Index: 5597612 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2350. Min Range: -5.2350
Max Act: 4.8600. Min Act: -0.1700
Data Index: 2275641 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2350. Min Range: -5.2350
Max Act: 4.8600. Min Act: -0.1700
Data Index: 5644380 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2350. Min Range: -5.2350
Max Act: 4.8912. Min Act: -0.1700
Data Index: 6561827 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2350. Min Range: -5.2350
Max Act: 4.8287. Min Act: -0.1700
Data Index: 7815499 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2350. Min Range: -5.2350
Max Act: 4.8287. Min Act: -0.1700
Data Index: 8701718 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2350. Min Range: -5.2350
Max Act: 4.7975. Min Act: -0.1700
Data Index: 4375387 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2350. Min Range: -5.2350
Max Act: 4.8287. Min Act: -0.1700
Data Index: 2311243 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2350. Min Range: -5.2350
Max Act: 4.7975. Min Act: -0.1700
Data Index: 2699178 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2350. Min Range: -5.2350
Max Act: 4.7975. Min Act: -0.1700
Data Index: 8171224 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2350. Min Range: -5.2350
Max Act: 4.7975. Min Act: -0.1700
Data Index: 4758135 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2350. Min Range: -5.2350
Max Act: 4.7975. Min Act: -0.1700
Data Index: 4938580 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2350. Min Range: -5.2350
Max Act: 4.7975. Min Act: -0.1700
Data Index: 3443302 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2350. Min Range: -5.2350
Max Act: 4.7975. Min Act: -0.1700
Data Index: 1606647 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2350. Min Range: -5.2350
Max Act: 4.7662. Min Act: -0.1700
Data Index: 3480535 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19