Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1951 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1051. Min Range: -7.1051
Max Act: 7.0739. Min Act: -0.1700
Data Index: 710180 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1051. Min Range: -7.1051
Max Act: 7.1051. Min Act: -0.1700
Data Index: 1561162 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1051. Min Range: -7.1051
Max Act: 7.0739. Min Act: -0.1700
Data Index: 274629 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1051. Min Range: -7.1051
Max Act: 7.0739. Min Act: -0.1700
Data Index: 8338436 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1051. Min Range: -7.1051
Max Act: 7.0426. Min Act: -0.1700
Data Index: 954110 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1051. Min Range: -7.1051
Max Act: 6.9176. Min Act: -0.1700
Data Index: 3289606 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1051. Min Range: -7.1051
Max Act: 6.9176. Min Act: -0.1700
Data Index: 222387 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1051. Min Range: -7.1051
Max Act: 6.9176. Min Act: -0.1700
Data Index: 7868831 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1051. Min Range: -7.1051
Max Act: 6.9176. Min Act: -0.1700
Data Index: 347352 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1051. Min Range: -7.1051
Max Act: 6.9176. Min Act: -0.1700
Data Index: 4675889 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1051. Min Range: -7.1051
Max Act: 6.8551. Min Act: -0.1700
Data Index: 8542635 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1051. Min Range: -7.1051
Max Act: 6.8551. Min Act: -0.1700
Data Index: 6120318 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1051. Min Range: -7.1051
Max Act: 6.8551. Min Act: -0.1700
Data Index: 2677589 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1051. Min Range: -7.1051
Max Act: 6.8551. Min Act: -0.1700
Data Index: 1287135 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1051. Min Range: -7.1051
Max Act: 6.8239. Min Act: -0.1700
Data Index: 4185339 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1051. Min Range: -7.1051
Max Act: 6.8239. Min Act: -0.1700
Data Index: 2036014 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1051. Min Range: -7.1051
Max Act: 6.8239. Min Act: -0.1700
Data Index: 6903680 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1051. Min Range: -7.1051
Max Act: 6.8239. Min Act: -0.1700
Data Index: 2858690 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1051. Min Range: -7.1051
Max Act: 6.7926. Min Act: -0.1700
Data Index: 2059275 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1051. Min Range: -7.1051
Max Act: 6.7926. Min Act: -0.1700
Data Index: 7551689 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19