Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1763 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8867. Min Range: -6.8867
Max Act: 6.8867. Min Act: -0.1700
Data Index: 1418256 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8867. Min Range: -6.8867
Max Act: 6.6367. Min Act: -0.1700
Data Index: 7466746 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8867. Min Range: -6.8867
Max Act: 6.5429. Min Act: -0.1700
Data Index: 7071944 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8867. Min Range: -6.8867
Max Act: 6.4492. Min Act: -0.1700
Data Index: 1013188 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8867. Min Range: -6.8867
Max Act: 6.4492. Min Act: -0.1700
Data Index: 310953 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8867. Min Range: -6.8867
Max Act: 6.4179. Min Act: -0.1700
Data Index: 6297448 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8867. Min Range: -6.8867
Max Act: 6.3867. Min Act: -0.1700
Data Index: 6308032 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8867. Min Range: -6.8867
Max Act: 6.4179. Min Act: -0.1700
Data Index: 5979745 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8867. Min Range: -6.8867
Max Act: 6.3554. Min Act: -0.1700
Data Index: 7845710 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8867. Min Range: -6.8867
Max Act: 6.3867. Min Act: -0.1700
Data Index: 1360747 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8867. Min Range: -6.8867
Max Act: 6.3867. Min Act: -0.1700
Data Index: 1040798 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8867. Min Range: -6.8867
Max Act: 6.3554. Min Act: -0.1700
Data Index: 5267898 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8867. Min Range: -6.8867
Max Act: 6.3554. Min Act: -0.1700
Data Index: 3189397 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8867. Min Range: -6.8867
Max Act: 6.3242. Min Act: -0.1700
Data Index: 6618283 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8867. Min Range: -6.8867
Max Act: 6.2929. Min Act: -0.1700
Data Index: 6520684 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8867. Min Range: -6.8867
Max Act: 6.2929. Min Act: -0.1700
Data Index: 720728 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8867. Min Range: -6.8867
Max Act: 6.2617. Min Act: -0.1700
Data Index: 548437 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8867. Min Range: -6.8867
Max Act: 6.2304. Min Act: -0.1700
Data Index: 5302222 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8867. Min Range: -6.8867
Max Act: 6.2617. Min Act: -0.1700
Data Index: 7288736 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8867. Min Range: -6.8867
Max Act: 6.1992. Min Act: -0.1700
Data Index: 1820365 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19