Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2745 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8600. Min Range: -1.8600
Max Act: 1.8600. Min Act: -0.1699
Data Index: 95691 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8600. Min Range: -1.8600
Max Act: 1.8600. Min Act: -0.1700
Data Index: 6923228 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8600. Min Range: -1.8600
Max Act: 1.7741. Min Act: -0.1700
Data Index: 6196489 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8600. Min Range: -1.8600
Max Act: 1.7827. Min Act: -0.1700
Data Index: 3626231 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8600. Min Range: -1.8600
Max Act: 1.7655. Min Act: -0.1700
Data Index: 3724328 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8600. Min Range: -1.8600
Max Act: 1.7482. Min Act: -0.1700
Data Index: 7355527 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8600. Min Range: -1.8600
Max Act: 1.7396. Min Act: -0.1700
Data Index: 2118316 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8600. Min Range: -1.8600
Max Act: 1.7309. Min Act: -0.1700
Data Index: 4192383 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8600. Min Range: -1.8600
Max Act: 1.7309. Min Act: -0.1700
Data Index: 3834837 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8600. Min Range: -1.8600
Max Act: 1.7309. Min Act: -0.1700
Data Index: 4034427 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8600. Min Range: -1.8600
Max Act: 1.7136. Min Act: -0.1700
Data Index: 1726869 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8600. Min Range: -1.8600
Max Act: 1.7136. Min Act: -0.1700
Data Index: 7577623 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8600. Min Range: -1.8600
Max Act: 1.7050. Min Act: -0.1700
Data Index: 2920338 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8600. Min Range: -1.8600
Max Act: 1.7136. Min Act: -0.1700
Data Index: 7856266 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8600. Min Range: -1.8600
Max Act: 1.7050. Min Act: -0.1700
Data Index: 792739 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8600. Min Range: -1.8600
Max Act: 1.6963. Min Act: -0.1700
Data Index: 1491027 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8600. Min Range: -1.8600
Max Act: 1.7136. Min Act: -0.1700
Data Index: 3454053 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8600. Min Range: -1.8600
Max Act: 1.7050. Min Act: -0.1700
Data Index: 7746495 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8600. Min Range: -1.8600
Max Act: 1.7050. Min Act: -0.1700
Data Index: 286389 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8600. Min Range: -1.8600
Max Act: 1.6876. Min Act: -0.1700
Data Index: 6738323 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19