Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3168 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0563. Min Range: -6.0563
Max Act: 6.0563. Min Act: -0.1700
Data Index: 8421379 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0563. Min Range: -6.0563
Max Act: 5.9938. Min Act: -0.1700
Data Index: 7090761 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0563. Min Range: -6.0563
Max Act: 5.9626. Min Act: -0.1700
Data Index: 3555496 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0563. Min Range: -6.0563
Max Act: 5.9626. Min Act: -0.1699
Data Index: 5992948 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0563. Min Range: -6.0563
Max Act: 5.9313. Min Act: -0.1700
Data Index: 3073597 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0563. Min Range: -6.0563
Max Act: 5.9001. Min Act: -0.1700
Data Index: 7518819 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0563. Min Range: -6.0563
Max Act: 5.9001. Min Act: -0.1700
Data Index: 8031578 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0563. Min Range: -6.0563
Max Act: 5.8688. Min Act: -0.1700
Data Index: 1133347 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0563. Min Range: -6.0563
Max Act: 5.8688. Min Act: -0.1700
Data Index: 1210626 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0563. Min Range: -6.0563
Max Act: 5.8688. Min Act: -0.1700
Data Index: 4491295 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0563. Min Range: -6.0563
Max Act: 5.8688. Min Act: -0.1700
Data Index: 5378751 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0563. Min Range: -6.0563
Max Act: 5.8376. Min Act: -0.1700
Data Index: 8819672 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0563. Min Range: -6.0563
Max Act: 5.8376. Min Act: -0.1700
Data Index: 963650 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0563. Min Range: -6.0563
Max Act: 5.8376. Min Act: -0.1700
Data Index: 3234407 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0563. Min Range: -6.0563
Max Act: 5.8063. Min Act: -0.1700
Data Index: 6442940 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0563. Min Range: -6.0563
Max Act: 5.8376. Min Act: -0.1700
Data Index: 8822023 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0563. Min Range: -6.0563
Max Act: 5.8688. Min Act: -0.1700
Data Index: 8810388 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0563. Min Range: -6.0563
Max Act: 5.8063. Min Act: -0.1700
Data Index: 8285736 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0563. Min Range: -6.0563
Max Act: 5.8063. Min Act: -0.1700
Data Index: 8273837 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0563. Min Range: -6.0563
Max Act: 5.8376. Min Act: -0.1700
Data Index: 3555504 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19