Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6371 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6441. Min Range: -8.6441
Max Act: 8.6441. Min Act: -0.1700
Data Index: 7890606 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6441. Min Range: -8.6441
Max Act: 8.3316. Min Act: -0.1700
Data Index: 2169275 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6441. Min Range: -8.6441
Max Act: 8.2691. Min Act: -0.1700
Data Index: 2826634 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6441. Min Range: -8.6441
Max Act: 8.2691. Min Act: -0.1700
Data Index: 3847736 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6441. Min Range: -8.6441
Max Act: 8.2066. Min Act: -0.1700
Data Index: 2744378 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6441. Min Range: -8.6441
Max Act: 8.2066. Min Act: -0.1700
Data Index: 3429300 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6441. Min Range: -8.6441
Max Act: 8.0816. Min Act: -0.1700
Data Index: 2787656 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6441. Min Range: -8.6441
Max Act: 8.1441. Min Act: -0.1700
Data Index: 4032151 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6441. Min Range: -8.6441
Max Act: 8.1441. Min Act: -0.1700
Data Index: 8589758 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6441. Min Range: -8.6441
Max Act: 8.1441. Min Act: -0.1700
Data Index: 186711 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6441. Min Range: -8.6441
Max Act: 8.1441. Min Act: -0.1700
Data Index: 2950054 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6441. Min Range: -8.6441
Max Act: 8.0816. Min Act: -0.1700
Data Index: 8289220 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6441. Min Range: -8.6441
Max Act: 8.0816. Min Act: -0.1700
Data Index: 786292 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6441. Min Range: -8.6441
Max Act: 8.0816. Min Act: -0.1700
Data Index: 5608051 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6441. Min Range: -8.6441
Max Act: 8.0191. Min Act: -0.1700
Data Index: 4368598 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6441. Min Range: -8.6441
Max Act: 8.0191. Min Act: -0.1700
Data Index: 2974809 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6441. Min Range: -8.6441
Max Act: 8.0191. Min Act: -0.1700
Data Index: 2067388 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6441. Min Range: -8.6441
Max Act: 7.9566. Min Act: -0.1700
Data Index: 1233852 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6441. Min Range: -8.6441
Max Act: 7.9566. Min Act: -0.1700
Data Index: 3455129 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6441. Min Range: -8.6441
Max Act: 7.9566. Min Act: -0.1700
Data Index: 3501348 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19