Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3403 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1847. Min Range: -5.1847
Max Act: 5.1847. Min Act: -0.1700
Data Index: 6875658 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1847. Min Range: -5.1847
Max Act: 5.1535. Min Act: -0.1700
Data Index: 3807334 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1847. Min Range: -5.1847
Max Act: 5.1847. Min Act: -0.1700
Data Index: 7837184 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1847. Min Range: -5.1847
Max Act: 5.1222. Min Act: -0.1700
Data Index: 3542565 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1847. Min Range: -5.1847
Max Act: 5.1222. Min Act: -0.1700
Data Index: 4434286 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1847. Min Range: -5.1847
Max Act: 5.1535. Min Act: -0.1700
Data Index: 8339992 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1847. Min Range: -5.1847
Max Act: 5.1222. Min Act: -0.1700
Data Index: 4866705 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1847. Min Range: -5.1847
Max Act: 5.0910. Min Act: -0.1700
Data Index: 507663 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1847. Min Range: -5.1847
Max Act: 5.0597. Min Act: -0.1700
Data Index: 2286596 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1847. Min Range: -5.1847
Max Act: 4.9972. Min Act: -0.1700
Data Index: 5911794 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1847. Min Range: -5.1847
Max Act: 4.9972. Min Act: -0.1700
Data Index: 6728208 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1847. Min Range: -5.1847
Max Act: 4.9972. Min Act: -0.1700
Data Index: 1190767 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1847. Min Range: -5.1847
Max Act: 4.9660. Min Act: -0.1700
Data Index: 7355015 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1847. Min Range: -5.1847
Max Act: 4.9972. Min Act: -0.1700
Data Index: 1437690 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1847. Min Range: -5.1847
Max Act: 4.9660. Min Act: -0.1700
Data Index: 2734246 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1847. Min Range: -5.1847
Max Act: 4.9972. Min Act: -0.1700
Data Index: 367096 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1847. Min Range: -5.1847
Max Act: 4.9660. Min Act: -0.1700
Data Index: 3547648 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1847. Min Range: -5.1847
Max Act: 4.9660. Min Act: -0.1700
Data Index: 8702766 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1847. Min Range: -5.1847
Max Act: 4.9660. Min Act: -0.1700
Data Index: 5499441 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1847. Min Range: -5.1847
Max Act: 4.9035. Min Act: -0.1700
Data Index: 6467254 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19