Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1778 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1104. Min Range: -6.1104
Max Act: 6.1104. Min Act: -0.1700
Data Index: 55546 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1104. Min Range: -6.1104
Max Act: 5.9854. Min Act: -0.1700
Data Index: 8477000 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1104. Min Range: -6.1104
Max Act: 5.9542. Min Act: -0.1700
Data Index: 6647610 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1104. Min Range: -6.1104
Max Act: 5.8917. Min Act: -0.1700
Data Index: 6495606 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1104. Min Range: -6.1104
Max Act: 5.7979. Min Act: -0.1700
Data Index: 561675 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1104. Min Range: -6.1104
Max Act: 5.7979. Min Act: -0.1700
Data Index: 327677 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1104. Min Range: -6.1104
Max Act: 5.7667. Min Act: -0.1700
Data Index: 853077 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1104. Min Range: -6.1104
Max Act: 5.7667. Min Act: -0.1700
Data Index: 1874697 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1104. Min Range: -6.1104
Max Act: 5.7354. Min Act: -0.1700
Data Index: 4983657 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1104. Min Range: -6.1104
Max Act: 5.7354. Min Act: -0.1700
Data Index: 4411444 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1104. Min Range: -6.1104
Max Act: 5.7354. Min Act: -0.1700
Data Index: 1690679 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1104. Min Range: -6.1104
Max Act: 5.6729. Min Act: -0.1700
Data Index: 2374290 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1104. Min Range: -6.1104
Max Act: 5.7042. Min Act: -0.1700
Data Index: 1841818 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1104. Min Range: -6.1104
Max Act: 5.7042. Min Act: -0.1700
Data Index: 4841522 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1104. Min Range: -6.1104
Max Act: 5.7042. Min Act: -0.1700
Data Index: 5273308 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1104. Min Range: -6.1104
Max Act: 5.6729. Min Act: -0.1700
Data Index: 8770814 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1104. Min Range: -6.1104
Max Act: 5.6729. Min Act: -0.1700
Data Index: 4794291 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1104. Min Range: -6.1104
Max Act: 5.6729. Min Act: -0.1700
Data Index: 3230036 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1104. Min Range: -6.1104
Max Act: 5.6729. Min Act: -0.1700
Data Index: 6453217 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1104. Min Range: -6.1104
Max Act: 5.6417. Min Act: -0.1700
Data Index: 2639155 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19