Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1396 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3551. Min Range: -6.3551
Max Act: 6.3551. Min Act: -0.1700
Data Index: 1227320 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3551. Min Range: -6.3551
Max Act: 6.1676. Min Act: -0.1700
Data Index: 2617208 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3551. Min Range: -6.3551
Max Act: 6.1051. Min Act: -0.1700
Data Index: 7762743 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3551. Min Range: -6.3551
Max Act: 6.1051. Min Act: -0.1700
Data Index: 3150200 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3551. Min Range: -6.3551
Max Act: 5.9801. Min Act: -0.1700
Data Index: 1805741 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3551. Min Range: -6.3551
Max Act: 6.0114. Min Act: -0.1700
Data Index: 907867 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3551. Min Range: -6.3551
Max Act: 5.9489. Min Act: -0.1700
Data Index: 434546 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3551. Min Range: -6.3551
Max Act: 5.9489. Min Act: -0.1700
Data Index: 2503970 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3551. Min Range: -6.3551
Max Act: 5.8239. Min Act: -0.1700
Data Index: 4570785 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3551. Min Range: -6.3551
Max Act: 5.8239. Min Act: -0.1700
Data Index: 5429603 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3551. Min Range: -6.3551
Max Act: 5.8239. Min Act: -0.1700
Data Index: 2387899 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3551. Min Range: -6.3551
Max Act: 5.7926. Min Act: -0.1700
Data Index: 8310726 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3551. Min Range: -6.3551
Max Act: 5.7614. Min Act: -0.1700
Data Index: 4855883 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3551. Min Range: -6.3551
Max Act: 5.7614. Min Act: -0.1700
Data Index: 4190916 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3551. Min Range: -6.3551
Max Act: 5.6989. Min Act: -0.1700
Data Index: 7649190 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3551. Min Range: -6.3551
Max Act: 5.6989. Min Act: -0.1700
Data Index: 2480616 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3551. Min Range: -6.3551
Max Act: 5.6989. Min Act: -0.1700
Data Index: 5233599 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3551. Min Range: -6.3551
Max Act: 5.6676. Min Act: -0.1700
Data Index: 5233598 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3551. Min Range: -6.3551
Max Act: 5.6989. Min Act: -0.1700
Data Index: 1106887 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3551. Min Range: -6.3551
Max Act: 5.6364. Min Act: -0.1700
Data Index: 8109316 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19