Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3383 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9717. Min Range: -5.9717
Max Act: 5.9717. Min Act: -0.1700
Data Index: 3083508 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9717. Min Range: -5.9717
Max Act: 5.9092. Min Act: -0.1700
Data Index: 5643865 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9717. Min Range: -5.9717
Max Act: 5.8779. Min Act: -0.1700
Data Index: 5172989 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9717. Min Range: -5.9717
Max Act: 5.8467. Min Act: -0.1700
Data Index: 8103014 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9717. Min Range: -5.9717
Max Act: 5.8154. Min Act: -0.1700
Data Index: 7972355 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9717. Min Range: -5.9717
Max Act: 5.8154. Min Act: -0.1700
Data Index: 5054254 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9717. Min Range: -5.9717
Max Act: 5.7842. Min Act: -0.1700
Data Index: 8315591 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9717. Min Range: -5.9717
Max Act: 5.7529. Min Act: -0.1700
Data Index: 2707237 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9717. Min Range: -5.9717
Max Act: 5.7842. Min Act: -0.1700
Data Index: 446553 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9717. Min Range: -5.9717
Max Act: 5.7842. Min Act: -0.1700
Data Index: 2796944 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9717. Min Range: -5.9717
Max Act: 5.7217. Min Act: -0.1700
Data Index: 5759607 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9717. Min Range: -5.9717
Max Act: 5.7217. Min Act: -0.1700
Data Index: 2105181 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9717. Min Range: -5.9717
Max Act: 5.7217. Min Act: -0.1700
Data Index: 2631708 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9717. Min Range: -5.9717
Max Act: 5.6904. Min Act: -0.1700
Data Index: 5125566 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9717. Min Range: -5.9717
Max Act: 5.6904. Min Act: -0.1700
Data Index: 5493114 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9717. Min Range: -5.9717
Max Act: 5.7217. Min Act: -0.1700
Data Index: 1320339 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9717. Min Range: -5.9717
Max Act: 5.6904. Min Act: -0.1700
Data Index: 2965433 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9717. Min Range: -5.9717
Max Act: 5.6904. Min Act: -0.1700
Data Index: 3727443 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9717. Min Range: -5.9717
Max Act: 5.6592. Min Act: -0.1700
Data Index: 4183719 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9717. Min Range: -5.9717
Max Act: 5.6592. Min Act: -0.1700
Data Index: 8181363 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19