Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3666 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0797. Min Range: -8.0797
Max Act: 8.0797. Min Act: -0.1700
Data Index: 5113179 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0797. Min Range: -8.0797
Max Act: 7.9547. Min Act: -0.1700
Data Index: 3694397 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0797. Min Range: -8.0797
Max Act: 7.8922. Min Act: -0.1700
Data Index: 4634647 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0797. Min Range: -8.0797
Max Act: 7.8297. Min Act: -0.1700
Data Index: 4454962 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0797. Min Range: -8.0797
Max Act: 7.8297. Min Act: -0.1700
Data Index: 3079447 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0797. Min Range: -8.0797
Max Act: 7.8297. Min Act: -0.1700
Data Index: 3393327 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0797. Min Range: -8.0797
Max Act: 7.8922. Min Act: -0.1700
Data Index: 3248939 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0797. Min Range: -8.0797
Max Act: 7.7984. Min Act: -0.1700
Data Index: 7726947 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0797. Min Range: -8.0797
Max Act: 7.7672. Min Act: -0.1700
Data Index: 4996113 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0797. Min Range: -8.0797
Max Act: 7.7359. Min Act: -0.1700
Data Index: 2967813 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0797. Min Range: -8.0797
Max Act: 7.7359. Min Act: -0.1700
Data Index: 5619949 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0797. Min Range: -8.0797
Max Act: 7.7359. Min Act: -0.1700
Data Index: 7130702 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0797. Min Range: -8.0797
Max Act: 7.7359. Min Act: -0.1700
Data Index: 5475662 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0797. Min Range: -8.0797
Max Act: 7.7672. Min Act: -0.1700
Data Index: 5625240 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0797. Min Range: -8.0797
Max Act: 7.7047. Min Act: -0.1700
Data Index: 3943114 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0797. Min Range: -8.0797
Max Act: 7.7047. Min Act: -0.1700
Data Index: 5078997 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0797. Min Range: -8.0797
Max Act: 7.7047. Min Act: -0.1700
Data Index: 421302 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0797. Min Range: -8.0797
Max Act: 7.7047. Min Act: -0.1700
Data Index: 2058260 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0797. Min Range: -8.0797
Max Act: 7.6422. Min Act: -0.1700
Data Index: 5333743 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0797. Min Range: -8.0797
Max Act: 7.6734. Min Act: -0.1700
Data Index: 2566277 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19