Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 677 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9148. Min Range: -3.9148
Max Act: 3.9148. Min Act: -0.1700
Data Index: 532745 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9148. Min Range: -3.9148
Max Act: 3.8366. Min Act: -0.1700
Data Index: 3714580 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9148. Min Range: -3.9148
Max Act: 3.8053. Min Act: -0.1700
Data Index: 6155052 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9148. Min Range: -3.9148
Max Act: 3.8053. Min Act: -0.1700
Data Index: 5385987 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9148. Min Range: -3.9148
Max Act: 3.7897. Min Act: -0.1700
Data Index: 197209 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9148. Min Range: -3.9148
Max Act: 3.7897. Min Act: -0.1700
Data Index: 4320360 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9148. Min Range: -3.9148
Max Act: 3.8053. Min Act: -0.1700
Data Index: 532746 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9148. Min Range: -3.9148
Max Act: 3.7741. Min Act: -0.1700
Data Index: 2521998 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9148. Min Range: -3.9148
Max Act: 3.7584. Min Act: -0.1700
Data Index: 3566655 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9148. Min Range: -3.9148
Max Act: 3.7584. Min Act: -0.1700
Data Index: 3910341 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9148. Min Range: -3.9148
Max Act: 3.7584. Min Act: -0.1700
Data Index: 532758 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9148. Min Range: -3.9148
Max Act: 3.7115. Min Act: -0.1700
Data Index: 4211459 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9148. Min Range: -3.9148
Max Act: 3.7115. Min Act: -0.1700
Data Index: 321072 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9148. Min Range: -3.9148
Max Act: 3.7115. Min Act: -0.1700
Data Index: 4898177 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9148. Min Range: -3.9148
Max Act: 3.6958. Min Act: -0.1700
Data Index: 3200030 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9148. Min Range: -3.9148
Max Act: 3.6958. Min Act: -0.1700
Data Index: 4022586 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9148. Min Range: -3.9148
Max Act: 3.6958. Min Act: -0.1700
Data Index: 2622121 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9148. Min Range: -3.9148
Max Act: 3.6802. Min Act: -0.1700
Data Index: 7915053 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9148. Min Range: -3.9148
Max Act: 3.6646. Min Act: -0.1700
Data Index: 4814232 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9148. Min Range: -3.9148
Max Act: 3.6646. Min Act: -0.1700
Data Index: 5143094 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19