Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3591 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5232. Min Range: -7.5232
Max Act: 7.5232. Min Act: -0.1700
Data Index: 2860583 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5232. Min Range: -7.5232
Max Act: 6.9920. Min Act: -0.1700
Data Index: 5370983 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5232. Min Range: -7.5232
Max Act: 6.8982. Min Act: -0.1700
Data Index: 5824397 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5232. Min Range: -7.5232
Max Act: 6.9295. Min Act: -0.1700
Data Index: 3702641 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5232. Min Range: -7.5232
Max Act: 6.8357. Min Act: -0.1700
Data Index: 1367044 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5232. Min Range: -7.5232
Max Act: 6.7732. Min Act: -0.1700
Data Index: 6386369 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5232. Min Range: -7.5232
Max Act: 6.8045. Min Act: -0.1700
Data Index: 2891731 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5232. Min Range: -7.5232
Max Act: 6.7107. Min Act: -0.1700
Data Index: 55777 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5232. Min Range: -7.5232
Max Act: 6.6170. Min Act: -0.1700
Data Index: 7102311 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5232. Min Range: -7.5232
Max Act: 6.5545. Min Act: -0.1700
Data Index: 2044950 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5232. Min Range: -7.5232
Max Act: 6.5545. Min Act: -0.1700
Data Index: 3244685 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5232. Min Range: -7.5232
Max Act: 6.5545. Min Act: -0.1700
Data Index: 4122332 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5232. Min Range: -7.5232
Max Act: 6.5232. Min Act: -0.1700
Data Index: 7374501 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5232. Min Range: -7.5232
Max Act: 6.5232. Min Act: -0.1700
Data Index: 4510419 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5232. Min Range: -7.5232
Max Act: 6.5232. Min Act: -0.1700
Data Index: 807590 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5232. Min Range: -7.5232
Max Act: 6.4920. Min Act: -0.1700
Data Index: 4118199 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5232. Min Range: -7.5232
Max Act: 6.4920. Min Act: -0.1700
Data Index: 7741858 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5232. Min Range: -7.5232
Max Act: 6.4920. Min Act: -0.1700
Data Index: 4657379 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5232. Min Range: -7.5232
Max Act: 6.4920. Min Act: -0.1700
Data Index: 2740620 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5232. Min Range: -7.5232
Max Act: 6.4607. Min Act: -0.1700
Data Index: 5564540 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19