Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3897 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6124. Min Range: -7.6124
Max Act: 7.6124. Min Act: -0.1700
Data Index: 2775044 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6124. Min Range: -7.6124
Max Act: 7.6124. Min Act: -0.1700
Data Index: 7245745 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6124. Min Range: -7.6124
Max Act: 7.4561. Min Act: -0.1700
Data Index: 5371845 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6124. Min Range: -7.6124
Max Act: 7.3311. Min Act: -0.1700
Data Index: 1746912 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6124. Min Range: -7.6124
Max Act: 7.1749. Min Act: -0.1700
Data Index: 932103 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6124. Min Range: -7.6124
Max Act: 7.1124. Min Act: -0.1700
Data Index: 3852465 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6124. Min Range: -7.6124
Max Act: 7.1124. Min Act: -0.1700
Data Index: 2674672 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6124. Min Range: -7.6124
Max Act: 7.1436. Min Act: -0.1700
Data Index: 3066154 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6124. Min Range: -7.6124
Max Act: 7.1124. Min Act: -0.1700
Data Index: 1792022 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6124. Min Range: -7.6124
Max Act: 7.0499. Min Act: -0.1700
Data Index: 5499994 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6124. Min Range: -7.6124
Max Act: 7.0499. Min Act: -0.1700
Data Index: 5527094 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6124. Min Range: -7.6124
Max Act: 7.0186. Min Act: -0.1700
Data Index: 3404126 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6124. Min Range: -7.6124
Max Act: 7.0499. Min Act: -0.1700
Data Index: 335812 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6124. Min Range: -7.6124
Max Act: 7.0499. Min Act: -0.1700
Data Index: 7310095 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6124. Min Range: -7.6124
Max Act: 7.0499. Min Act: -0.1700
Data Index: 8549004 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6124. Min Range: -7.6124
Max Act: 7.0499. Min Act: -0.1700
Data Index: 8268306 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6124. Min Range: -7.6124
Max Act: 7.0186. Min Act: -0.1700
Data Index: 4725832 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6124. Min Range: -7.6124
Max Act: 6.9874. Min Act: -0.1700
Data Index: 6293710 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6124. Min Range: -7.6124
Max Act: 6.9874. Min Act: -0.1700
Data Index: 1972307 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6124. Min Range: -7.6124
Max Act: 6.9561. Min Act: -0.1700
Data Index: 4743047 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19