Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 582 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2888. Min Range: -7.2888
Max Act: 7.2888. Min Act: -0.1700
Data Index: 7885640 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2888. Min Range: -7.2888
Max Act: 6.4763. Min Act: -0.1700
Data Index: 5368943 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2888. Min Range: -7.2888
Max Act: 6.4450. Min Act: -0.1700
Data Index: 6057295 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2888. Min Range: -7.2888
Max Act: 6.4450. Min Act: -0.1700
Data Index: 7967221 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2888. Min Range: -7.2888
Max Act: 6.4138. Min Act: -0.1700
Data Index: 3331514 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2888. Min Range: -7.2888
Max Act: 6.4138. Min Act: -0.1700
Data Index: 392737 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2888. Min Range: -7.2888
Max Act: 6.3825. Min Act: -0.1700
Data Index: 2696053 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2888. Min Range: -7.2888
Max Act: 6.3825. Min Act: -0.1700
Data Index: 4887332 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2888. Min Range: -7.2888
Max Act: 6.3825. Min Act: -0.1700
Data Index: 715420 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2888. Min Range: -7.2888
Max Act: 6.3200. Min Act: -0.1700
Data Index: 853791 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2888. Min Range: -7.2888
Max Act: 6.3200. Min Act: -0.1700
Data Index: 4227667 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2888. Min Range: -7.2888
Max Act: 6.2888. Min Act: -0.1700
Data Index: 1145001 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2888. Min Range: -7.2888
Max Act: 6.2888. Min Act: -0.1700
Data Index: 7967220 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2888. Min Range: -7.2888
Max Act: 6.2888. Min Act: -0.1700
Data Index: 6425810 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2888. Min Range: -7.2888
Max Act: 6.2888. Min Act: -0.1700
Data Index: 8645300 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2888. Min Range: -7.2888
Max Act: 6.2575. Min Act: -0.1700
Data Index: 6626254 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2888. Min Range: -7.2888
Max Act: 6.1950. Min Act: -0.1700
Data Index: 29449 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2888. Min Range: -7.2888
Max Act: 6.1950. Min Act: -0.1700
Data Index: 4750282 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2888. Min Range: -7.2888
Max Act: 6.1950. Min Act: -0.1700
Data Index: 2026387 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2888. Min Range: -7.2888
Max Act: 6.1950. Min Act: -0.1700
Data Index: 7159501 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19