Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3044 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6966. Min Range: -7.6966
Max Act: 7.6966. Min Act: -0.1700
Data Index: 6478772 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6966. Min Range: -7.6966
Max Act: 7.4778. Min Act: -0.1700
Data Index: 1746237 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6966. Min Range: -7.6966
Max Act: 7.4466. Min Act: -0.1700
Data Index: 1759292 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6966. Min Range: -7.6966
Max Act: 7.4778. Min Act: -0.1700
Data Index: 7371473 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6966. Min Range: -7.6966
Max Act: 7.4153. Min Act: -0.1700
Data Index: 1596955 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6966. Min Range: -7.6966
Max Act: 7.3841. Min Act: -0.1700
Data Index: 5865931 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6966. Min Range: -7.6966
Max Act: 7.1341. Min Act: -0.1700
Data Index: 6559126 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6966. Min Range: -7.6966
Max Act: 7.1341. Min Act: -0.1700
Data Index: 7392032 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6966. Min Range: -7.6966
Max Act: 7.1028. Min Act: -0.1700
Data Index: 5273889 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6966. Min Range: -7.6966
Max Act: 7.0403. Min Act: -0.1700
Data Index: 2966021 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6966. Min Range: -7.6966
Max Act: 7.0403. Min Act: -0.1700
Data Index: 1302394 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6966. Min Range: -7.6966
Max Act: 7.0716. Min Act: -0.1700
Data Index: 1028629 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6966. Min Range: -7.6966
Max Act: 7.0091. Min Act: -0.1700
Data Index: 7853300 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6966. Min Range: -7.6966
Max Act: 7.0403. Min Act: -0.1700
Data Index: 7010162 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6966. Min Range: -7.6966
Max Act: 7.0091. Min Act: -0.1700
Data Index: 1991064 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6966. Min Range: -7.6966
Max Act: 6.9153. Min Act: -0.1700
Data Index: 2942972 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6966. Min Range: -7.6966
Max Act: 6.9153. Min Act: -0.1700
Data Index: 4217735 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6966. Min Range: -7.6966
Max Act: 6.9466. Min Act: -0.1700
Data Index: 4660760 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6966. Min Range: -7.6966
Max Act: 6.9153. Min Act: -0.1700
Data Index: 3543112 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6966. Min Range: -7.6966
Max Act: 6.9153. Min Act: -0.1700
Data Index: 2424797 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19