Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3248 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0077. Min Range: -6.0077
Max Act: 6.0077. Min Act: -0.1700
Data Index: 8069362 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0077. Min Range: -6.0077
Max Act: 6.0077. Min Act: -0.1700
Data Index: 5115893 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0077. Min Range: -6.0077
Max Act: 5.9140. Min Act: -0.1700
Data Index: 4054651 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0077. Min Range: -6.0077
Max Act: 5.8827. Min Act: -0.1700
Data Index: 68727 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0077. Min Range: -6.0077
Max Act: 5.8202. Min Act: -0.1700
Data Index: 5667899 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0077. Min Range: -6.0077
Max Act: 5.7890. Min Act: -0.1700
Data Index: 384395 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0077. Min Range: -6.0077
Max Act: 5.7890. Min Act: -0.1700
Data Index: 8538729 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0077. Min Range: -6.0077
Max Act: 5.7577. Min Act: -0.1700
Data Index: 5484484 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0077. Min Range: -6.0077
Max Act: 5.6952. Min Act: -0.1700
Data Index: 989119 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0077. Min Range: -6.0077
Max Act: 5.6952. Min Act: -0.1700
Data Index: 2371943 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0077. Min Range: -6.0077
Max Act: 5.6952. Min Act: -0.1700
Data Index: 4765799 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0077. Min Range: -6.0077
Max Act: 5.6640. Min Act: -0.1700
Data Index: 7940371 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0077. Min Range: -6.0077
Max Act: 5.5702. Min Act: -0.1700
Data Index: 8263545 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0077. Min Range: -6.0077
Max Act: 5.5702. Min Act: -0.1700
Data Index: 957537 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0077. Min Range: -6.0077
Max Act: 5.5702. Min Act: -0.1700
Data Index: 8815986 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0077. Min Range: -6.0077
Max Act: 5.5702. Min Act: -0.1700
Data Index: 4499622 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0077. Min Range: -6.0077
Max Act: 5.5390. Min Act: -0.1700
Data Index: 4260080 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0077. Min Range: -6.0077
Max Act: 5.5702. Min Act: -0.1700
Data Index: 1033194 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0077. Min Range: -6.0077
Max Act: 5.5702. Min Act: -0.1700
Data Index: 6200668 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0077. Min Range: -6.0077
Max Act: 5.5077. Min Act: -0.1700
Data Index: 4792053 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19