Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3418 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1261. Min Range: -6.1261
Max Act: 6.1261. Min Act: -0.1700
Data Index: 185940 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1261. Min Range: -6.1261
Max Act: 5.9386. Min Act: -0.1700
Data Index: 5026174 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1261. Min Range: -6.1261
Max Act: 5.8448. Min Act: -0.1700
Data Index: 6558075 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1261. Min Range: -6.1261
Max Act: 5.8136. Min Act: -0.1700
Data Index: 2712040 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1261. Min Range: -6.1261
Max Act: 5.8136. Min Act: -0.1700
Data Index: 7308023 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1261. Min Range: -6.1261
Max Act: 5.8448. Min Act: -0.1700
Data Index: 79702 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1261. Min Range: -6.1261
Max Act: 5.7823. Min Act: -0.1700
Data Index: 5603421 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1261. Min Range: -6.1261
Max Act: 5.7823. Min Act: -0.1700
Data Index: 7516772 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1261. Min Range: -6.1261
Max Act: 5.7511. Min Act: -0.1700
Data Index: 6623094 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1261. Min Range: -6.1261
Max Act: 5.7198. Min Act: -0.1700
Data Index: 7875889 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1261. Min Range: -6.1261
Max Act: 5.7511. Min Act: -0.1700
Data Index: 5024056 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1261. Min Range: -6.1261
Max Act: 5.6886. Min Act: -0.1700
Data Index: 5512241 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1261. Min Range: -6.1261
Max Act: 5.6886. Min Act: -0.1700
Data Index: 7612162 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1261. Min Range: -6.1261
Max Act: 5.6573. Min Act: -0.1700
Data Index: 5869791 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1261. Min Range: -6.1261
Max Act: 5.6573. Min Act: -0.1700
Data Index: 5606764 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1261. Min Range: -6.1261
Max Act: 5.6261. Min Act: -0.1700
Data Index: 6566001 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1261. Min Range: -6.1261
Max Act: 5.5948. Min Act: -0.1700
Data Index: 2043096 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1261. Min Range: -6.1261
Max Act: 5.6261. Min Act: -0.1700
Data Index: 6374203 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1261. Min Range: -6.1261
Max Act: 5.6261. Min Act: -0.1700
Data Index: 6085571 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1261. Min Range: -6.1261
Max Act: 5.6573. Min Act: -0.1700
Data Index: 4140440 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19