Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 680 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9533. Min Range: -6.9533
Max Act: 6.9533. Min Act: -0.1700
Data Index: 3841546 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9533. Min Range: -6.9533
Max Act: 6.8908. Min Act: -0.1700
Data Index: 1355471 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9533. Min Range: -6.9533
Max Act: 6.8908. Min Act: -0.1700
Data Index: 4713898 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9533. Min Range: -6.9533
Max Act: 6.7970. Min Act: -0.1700
Data Index: 8774602 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9533. Min Range: -6.9533
Max Act: 6.8283. Min Act: -0.1700
Data Index: 8578078 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9533. Min Range: -6.9533
Max Act: 6.8283. Min Act: -0.1700
Data Index: 5671699 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9533. Min Range: -6.9533
Max Act: 6.7970. Min Act: -0.1700
Data Index: 788448 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9533. Min Range: -6.9533
Max Act: 6.7970. Min Act: -0.1700
Data Index: 7722958 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9533. Min Range: -6.9533
Max Act: 6.7345. Min Act: -0.1700
Data Index: 2019746 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9533. Min Range: -6.9533
Max Act: 6.7658. Min Act: -0.1700
Data Index: 547669 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9533. Min Range: -6.9533
Max Act: 6.7658. Min Act: -0.1700
Data Index: 2372420 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9533. Min Range: -6.9533
Max Act: 6.7658. Min Act: -0.1700
Data Index: 3952752 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9533. Min Range: -6.9533
Max Act: 6.7345. Min Act: -0.1700
Data Index: 8448741 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9533. Min Range: -6.9533
Max Act: 6.7345. Min Act: -0.1700
Data Index: 788449 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9533. Min Range: -6.9533
Max Act: 6.6408. Min Act: -0.1700
Data Index: 6509413 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9533. Min Range: -6.9533
Max Act: 6.6720. Min Act: -0.1700
Data Index: 163158 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9533. Min Range: -6.9533
Max Act: 6.7345. Min Act: -0.1700
Data Index: 163141 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9533. Min Range: -6.9533
Max Act: 6.6720. Min Act: -0.1700
Data Index: 2215816 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9533. Min Range: -6.9533
Max Act: 6.6720. Min Act: -0.1700
Data Index: 3366396 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9533. Min Range: -6.9533
Max Act: 6.6720. Min Act: -0.1700
Data Index: 6617946 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19