Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2334 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8925. Min Range: -4.8925
Max Act: 4.8925. Min Act: -0.1700
Data Index: 1498771 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8925. Min Range: -4.8925
Max Act: 4.8300. Min Act: -0.1700
Data Index: 4652094 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8925. Min Range: -4.8925
Max Act: 4.7987. Min Act: -0.1700
Data Index: 4156503 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8925. Min Range: -4.8925
Max Act: 4.7675. Min Act: -0.1700
Data Index: 1184922 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8925. Min Range: -4.8925
Max Act: 4.7050. Min Act: -0.1700
Data Index: 1666018 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8925. Min Range: -4.8925
Max Act: 4.7362. Min Act: -0.1700
Data Index: 6791022 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8925. Min Range: -4.8925
Max Act: 4.6425. Min Act: -0.1700
Data Index: 1498770 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8925. Min Range: -4.8925
Max Act: 4.6425. Min Act: -0.1700
Data Index: 3087357 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8925. Min Range: -4.8925
Max Act: 4.6425. Min Act: -0.1700
Data Index: 3772545 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8925. Min Range: -4.8925
Max Act: 4.6425. Min Act: -0.1700
Data Index: 827882 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8925. Min Range: -4.8925
Max Act: 4.6112. Min Act: -0.1700
Data Index: 1843590 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8925. Min Range: -4.8925
Max Act: 4.6425. Min Act: -0.1700
Data Index: 6891656 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8925. Min Range: -4.8925
Max Act: 4.6112. Min Act: -0.1700
Data Index: 509313 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8925. Min Range: -4.8925
Max Act: 4.6112. Min Act: -0.1700
Data Index: 3546705 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8925. Min Range: -4.8925
Max Act: 4.6112. Min Act: -0.1700
Data Index: 140894 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8925. Min Range: -4.8925
Max Act: 4.5800. Min Act: -0.1700
Data Index: 1123416 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8925. Min Range: -4.8925
Max Act: 4.5800. Min Act: -0.1700
Data Index: 4030953 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8925. Min Range: -4.8925
Max Act: 4.5487. Min Act: -0.1700
Data Index: 3049018 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8925. Min Range: -4.8925
Max Act: 4.5487. Min Act: -0.1700
Data Index: 4261148 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8925. Min Range: -4.8925
Max Act: 4.5487. Min Act: -0.1700
Data Index: 2251983 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19