Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3678 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1893. Min Range: -6.1893
Max Act: 6.1581. Min Act: -0.1700
Data Index: 5215471 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1893. Min Range: -6.1893
Max Act: 6.1268. Min Act: -0.1700
Data Index: 7624751 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1893. Min Range: -6.1893
Max Act: 6.1893. Min Act: -0.1700
Data Index: 134346 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1893. Min Range: -6.1893
Max Act: 6.0643. Min Act: -0.1700
Data Index: 2912579 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1893. Min Range: -6.1893
Max Act: 6.0643. Min Act: -0.1700
Data Index: 7472975 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1893. Min Range: -6.1893
Max Act: 6.0018. Min Act: -0.1700
Data Index: 6858823 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1893. Min Range: -6.1893
Max Act: 6.0331. Min Act: -0.1700
Data Index: 2129851 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1893. Min Range: -6.1893
Max Act: 6.0331. Min Act: -0.1700
Data Index: 4358736 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1893. Min Range: -6.1893
Max Act: 5.9706. Min Act: -0.1700
Data Index: 2237286 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1893. Min Range: -6.1893
Max Act: 5.9706. Min Act: -0.1700
Data Index: 3588295 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1893. Min Range: -6.1893
Max Act: 5.9393. Min Act: -0.1700
Data Index: 4422795 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1893. Min Range: -6.1893
Max Act: 5.9081. Min Act: -0.1700
Data Index: 5045251 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1893. Min Range: -6.1893
Max Act: 5.9081. Min Act: -0.1700
Data Index: 6585306 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1893. Min Range: -6.1893
Max Act: 5.8456. Min Act: -0.1700
Data Index: 2985632 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1893. Min Range: -6.1893
Max Act: 5.8768. Min Act: -0.1700
Data Index: 6287975 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1893. Min Range: -6.1893
Max Act: 5.8768. Min Act: -0.1700
Data Index: 249157 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1893. Min Range: -6.1893
Max Act: 5.8456. Min Act: -0.1700
Data Index: 2601766 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1893. Min Range: -6.1893
Max Act: 5.8143. Min Act: -0.1700
Data Index: 8215785 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1893. Min Range: -6.1893
Max Act: 5.8456. Min Act: -0.1700
Data Index: 1565797 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1893. Min Range: -6.1893
Max Act: 5.8456. Min Act: -0.1700
Data Index: 1019409 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19