Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5218 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2506. Min Range: -5.2506
Max Act: 5.2506. Min Act: -0.1700
Data Index: 2674104 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2506. Min Range: -5.2506
Max Act: 5.1881. Min Act: -0.1700
Data Index: 134772 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2506. Min Range: -5.2506
Max Act: 5.1569. Min Act: -0.1700
Data Index: 2907028 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2506. Min Range: -5.2506
Max Act: 5.1256. Min Act: -0.1700
Data Index: 3337566 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2506. Min Range: -5.2506
Max Act: 5.0944. Min Act: -0.1700
Data Index: 9530 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2506. Min Range: -5.2506
Max Act: 5.0944. Min Act: -0.1700
Data Index: 8500118 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2506. Min Range: -5.2506
Max Act: 5.0319. Min Act: -0.1700
Data Index: 3952332 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2506. Min Range: -5.2506
Max Act: 5.0006. Min Act: -0.1700
Data Index: 4057033 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2506. Min Range: -5.2506
Max Act: 5.0006. Min Act: -0.1700
Data Index: 8774378 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2506. Min Range: -5.2506
Max Act: 4.9694. Min Act: -0.1700
Data Index: 535683 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2506. Min Range: -5.2506
Max Act: 4.9694. Min Act: -0.1700
Data Index: 1441625 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2506. Min Range: -5.2506
Max Act: 4.9694. Min Act: -0.1700
Data Index: 7744348 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2506. Min Range: -5.2506
Max Act: 4.9694. Min Act: -0.1700
Data Index: 7503973 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2506. Min Range: -5.2506
Max Act: 4.9694. Min Act: -0.1700
Data Index: 3411633 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2506. Min Range: -5.2506
Max Act: 4.9694. Min Act: -0.1700
Data Index: 1049504 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2506. Min Range: -5.2506
Max Act: 4.9694. Min Act: -0.1700
Data Index: 2397264 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2506. Min Range: -5.2506
Max Act: 4.9694. Min Act: -0.1700
Data Index: 8084176 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2506. Min Range: -5.2506
Max Act: 4.9381. Min Act: -0.1700
Data Index: 7880864 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2506. Min Range: -5.2506
Max Act: 4.9069. Min Act: -0.1700
Data Index: 4365030 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2506. Min Range: -5.2506
Max Act: 4.9381. Min Act: -0.1700
Data Index: 1205877 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19