Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2772 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8405. Min Range: -4.8405
Max Act: 4.8405. Min Act: -0.1700
Data Index: 902206 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8405. Min Range: -4.8405
Max Act: 4.5592. Min Act: -0.1700
Data Index: 5385562 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8405. Min Range: -4.8405
Max Act: 4.4655. Min Act: -0.1700
Data Index: 8069838 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8405. Min Range: -4.8405
Max Act: 4.4967. Min Act: -0.1700
Data Index: 1039991 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8405. Min Range: -4.8405
Max Act: 4.4342. Min Act: -0.1700
Data Index: 1716242 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8405. Min Range: -4.8405
Max Act: 4.4030. Min Act: -0.1700
Data Index: 5694608 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8405. Min Range: -4.8405
Max Act: 4.3717. Min Act: -0.1700
Data Index: 909723 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8405. Min Range: -4.8405
Max Act: 4.3405. Min Act: -0.1700
Data Index: 8219138 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8405. Min Range: -4.8405
Max Act: 4.3717. Min Act: -0.1700
Data Index: 1945271 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8405. Min Range: -4.8405
Max Act: 4.3405. Min Act: -0.1700
Data Index: 3105807 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8405. Min Range: -4.8405
Max Act: 4.3405. Min Act: -0.1700
Data Index: 3125748 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8405. Min Range: -4.8405
Max Act: 4.3092. Min Act: -0.1700
Data Index: 7051084 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8405. Min Range: -4.8405
Max Act: 4.2780. Min Act: -0.1700
Data Index: 1400258 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8405. Min Range: -4.8405
Max Act: 4.2780. Min Act: -0.1700
Data Index: 8500619 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8405. Min Range: -4.8405
Max Act: 4.2467. Min Act: -0.1700
Data Index: 4768788 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8405. Min Range: -4.8405
Max Act: 4.2467. Min Act: -0.1700
Data Index: 6624076 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8405. Min Range: -4.8405
Max Act: 4.2780. Min Act: -0.1700
Data Index: 7920447 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8405. Min Range: -4.8405
Max Act: 4.2780. Min Act: -0.1700
Data Index: 2251154 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8405. Min Range: -4.8405
Max Act: 4.2780. Min Act: -0.1700
Data Index: 3940273 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8405. Min Range: -4.8405
Max Act: 4.2467. Min Act: -0.1700
Data Index: 4868464 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19