Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3303 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0047. Min Range: -5.0047
Max Act: 5.0047. Min Act: -0.1700
Data Index: 3922778 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0047. Min Range: -5.0047
Max Act: 4.9422. Min Act: -0.1700
Data Index: 1363848 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0047. Min Range: -5.0047
Max Act: 4.9734. Min Act: -0.1700
Data Index: 4114158 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0047. Min Range: -5.0047
Max Act: 4.9422. Min Act: -0.1700
Data Index: 8237193 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0047. Min Range: -5.0047
Max Act: 4.8797. Min Act: -0.1700
Data Index: 1629162 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0047. Min Range: -5.0047
Max Act: 4.8484. Min Act: -0.1700
Data Index: 5064064 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0047. Min Range: -5.0047
Max Act: 4.8484. Min Act: -0.1700
Data Index: 6987599 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0047. Min Range: -5.0047
Max Act: 4.8484. Min Act: -0.1700
Data Index: 4461657 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0047. Min Range: -5.0047
Max Act: 4.8172. Min Act: -0.1700
Data Index: 5386752 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0047. Min Range: -5.0047
Max Act: 4.8172. Min Act: -0.1700
Data Index: 6096912 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0047. Min Range: -5.0047
Max Act: 4.8172. Min Act: -0.1700
Data Index: 8142660 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0047. Min Range: -5.0047
Max Act: 4.7547. Min Act: -0.1700
Data Index: 6352285 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0047. Min Range: -5.0047
Max Act: 4.7859. Min Act: -0.1700
Data Index: 5706362 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0047. Min Range: -5.0047
Max Act: 4.7859. Min Act: -0.1700
Data Index: 4862719 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0047. Min Range: -5.0047
Max Act: 4.7547. Min Act: -0.1700
Data Index: 8415216 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0047. Min Range: -5.0047
Max Act: 4.7547. Min Act: -0.1700
Data Index: 2654409 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0047. Min Range: -5.0047
Max Act: 4.7547. Min Act: -0.1700
Data Index: 6396829 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0047. Min Range: -5.0047
Max Act: 4.7234. Min Act: -0.1700
Data Index: 4457061 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0047. Min Range: -5.0047
Max Act: 4.7547. Min Act: -0.1700
Data Index: 3638855 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0047. Min Range: -5.0047
Max Act: 4.6922. Min Act: -0.1700
Data Index: 2072999 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19