Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4789 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9813. Min Range: -5.9813
Max Act: 5.9813. Min Act: -0.1700
Data Index: 7009691 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9813. Min Range: -5.9813
Max Act: 5.9500. Min Act: -0.1700
Data Index: 5014924 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9813. Min Range: -5.9813
Max Act: 5.8250. Min Act: -0.1700
Data Index: 950176 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9813. Min Range: -5.9813
Max Act: 5.7625. Min Act: -0.1700
Data Index: 3438433 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9813. Min Range: -5.9813
Max Act: 5.7625. Min Act: -0.1700
Data Index: 4363327 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9813. Min Range: -5.9813
Max Act: 5.6688. Min Act: -0.1700
Data Index: 6363124 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9813. Min Range: -5.9813
Max Act: 5.7000. Min Act: -0.1700
Data Index: 4159748 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9813. Min Range: -5.9813
Max Act: 5.7000. Min Act: -0.1700
Data Index: 6568371 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9813. Min Range: -5.9813
Max Act: 5.6375. Min Act: -0.1700
Data Index: 7530753 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9813. Min Range: -5.9813
Max Act: 5.6063. Min Act: -0.1700
Data Index: 7738197 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9813. Min Range: -5.9813
Max Act: 5.5750. Min Act: -0.1700
Data Index: 2995163 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9813. Min Range: -5.9813
Max Act: 5.6063. Min Act: -0.1700
Data Index: 35572 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9813. Min Range: -5.9813
Max Act: 5.5438. Min Act: -0.1700
Data Index: 1304397 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9813. Min Range: -5.9813
Max Act: 5.5438. Min Act: -0.1700
Data Index: 134424 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9813. Min Range: -5.9813
Max Act: 5.5438. Min Act: -0.1700
Data Index: 2812398 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9813. Min Range: -5.9813
Max Act: 5.5438. Min Act: -0.1700
Data Index: 2056401 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9813. Min Range: -5.9813
Max Act: 5.5125. Min Act: -0.1700
Data Index: 600648 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9813. Min Range: -5.9813
Max Act: 5.5125. Min Act: -0.1700
Data Index: 6775289 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9813. Min Range: -5.9813
Max Act: 5.4813. Min Act: -0.1700
Data Index: 4810286 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9813. Min Range: -5.9813
Max Act: 5.5125. Min Act: -0.1700
Data Index: 4116430 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19