Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1223 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0261. Min Range: -7.0261
Max Act: 7.0261. Min Act: -0.1700
Data Index: 3882115 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.9636. Min Act: -0.1700
Data Index: 8409958 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.9011. Min Act: -0.1700
Data Index: 1137891 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.8698. Min Act: -0.1700
Data Index: 4392194 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.8386. Min Act: -0.1700
Data Index: 5937691 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.8073. Min Act: -0.1700
Data Index: 3215168 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.7448. Min Act: -0.1700
Data Index: 4453028 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.7761. Min Act: -0.1700
Data Index: 1784653 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.7761. Min Act: -0.1700
Data Index: 3954904 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.7761. Min Act: -0.1700
Data Index: 5044870 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.7448. Min Act: -0.1700
Data Index: 6445064 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.7136. Min Act: -0.1700
Data Index: 5252450 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.7136. Min Act: -0.1700
Data Index: 7526037 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.6823. Min Act: -0.1700
Data Index: 7874029 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.6823. Min Act: -0.1700
Data Index: 1434510 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.6823. Min Act: -0.1700
Data Index: 7765391 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.6823. Min Act: -0.1700
Data Index: 3417330 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.6823. Min Act: -0.1700
Data Index: 6942989 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.6823. Min Act: -0.1700
Data Index: 6902653 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0261. Min Range: -7.0261
Max Act: 6.6823. Min Act: -0.1700
Data Index: 2546479 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19