Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5944 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6657. Min Range: -4.6657
Max Act: 4.6657. Min Act: -0.1700
Data Index: 820605 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6657. Min Range: -4.6657
Max Act: 4.4157. Min Act: -0.1700
Data Index: 8778758 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6657. Min Range: -4.6657
Max Act: 4.3844. Min Act: -0.1700
Data Index: 770856 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6657. Min Range: -4.6657
Max Act: 4.3532. Min Act: -0.1700
Data Index: 3342222 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6657. Min Range: -4.6657
Max Act: 4.2594. Min Act: -0.1700
Data Index: 2476597 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6657. Min Range: -4.6657
Max Act: 4.2282. Min Act: -0.1700
Data Index: 5087486 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6657. Min Range: -4.6657
Max Act: 4.1969. Min Act: -0.1700
Data Index: 373555 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6657. Min Range: -4.6657
Max Act: 4.1657. Min Act: -0.1700
Data Index: 1822958 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6657. Min Range: -4.6657
Max Act: 4.1657. Min Act: -0.1700
Data Index: 2470339 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6657. Min Range: -4.6657
Max Act: 4.1344. Min Act: -0.1700
Data Index: 4416908 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6657. Min Range: -4.6657
Max Act: 4.1032. Min Act: -0.1700
Data Index: 1187596 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6657. Min Range: -4.6657
Max Act: 4.1032. Min Act: -0.1700
Data Index: 1609428 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6657. Min Range: -4.6657
Max Act: 4.1032. Min Act: -0.1700
Data Index: 3054551 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6657. Min Range: -4.6657
Max Act: 4.1032. Min Act: -0.1700
Data Index: 7658360 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6657. Min Range: -4.6657
Max Act: 4.0406. Min Act: -0.1700
Data Index: 5014007 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6657. Min Range: -4.6657
Max Act: 4.0719. Min Act: -0.1700
Data Index: 5931121 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6657. Min Range: -4.6657
Max Act: 4.0719. Min Act: -0.1700
Data Index: 6296806 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6657. Min Range: -4.6657
Max Act: 4.0719. Min Act: -0.1700
Data Index: 624460 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6657. Min Range: -4.6657
Max Act: 4.0719. Min Act: -0.1700
Data Index: 3074106 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6657. Min Range: -4.6657
Max Act: 4.0719. Min Act: -0.1700
Data Index: 1977057 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19