Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2172 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3054. Min Range: -4.3054
Max Act: 4.3054. Min Act: -0.1700
Data Index: 8546166 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3054. Min Range: -4.3054
Max Act: 4.1804. Min Act: -0.1700
Data Index: 4257932 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3054. Min Range: -4.3054
Max Act: 4.1804. Min Act: -0.1700
Data Index: 3943513 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3054. Min Range: -4.3054
Max Act: 4.0241. Min Act: -0.1700
Data Index: 5189451 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3054. Min Range: -4.3054
Max Act: 4.0241. Min Act: -0.1700
Data Index: 7462636 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3054. Min Range: -4.3054
Max Act: 3.9928. Min Act: -0.1700
Data Index: 2066925 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3054. Min Range: -4.3054
Max Act: 3.9616. Min Act: -0.1700
Data Index: 2533291 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3054. Min Range: -4.3054
Max Act: 3.9616. Min Act: -0.1700
Data Index: 6638567 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3054. Min Range: -4.3054
Max Act: 3.8990. Min Act: -0.1700
Data Index: 8742213 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3054. Min Range: -4.3054
Max Act: 3.8990. Min Act: -0.1700
Data Index: 4569071 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3054. Min Range: -4.3054
Max Act: 3.8678. Min Act: -0.1700
Data Index: 6452350 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3054. Min Range: -4.3054
Max Act: 3.8678. Min Act: -0.1700
Data Index: 926467 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3054. Min Range: -4.3054
Max Act: 3.8678. Min Act: -0.1700
Data Index: 1489958 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3054. Min Range: -4.3054
Max Act: 3.8365. Min Act: -0.1700
Data Index: 8778370 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3054. Min Range: -4.3054
Max Act: 3.8365. Min Act: -0.1700
Data Index: 8742206 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3054. Min Range: -4.3054
Max Act: 3.8365. Min Act: -0.1700
Data Index: 1621739 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3054. Min Range: -4.3054
Max Act: 3.8365. Min Act: -0.1700
Data Index: 2066923 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3054. Min Range: -4.3054
Max Act: 3.7740. Min Act: -0.1700
Data Index: 1785926 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3054. Min Range: -4.3054
Max Act: 3.8052. Min Act: -0.1700
Data Index: 371657 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3054. Min Range: -4.3054
Max Act: 3.8052. Min Act: -0.1700
Data Index: 5658832 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19