Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5377 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5500. Min Range: -6.5500
Max Act: 6.5500. Min Act: -0.1700
Data Index: 1210108 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5500. Min Range: -6.5500
Max Act: 6.3000. Min Act: -0.1700
Data Index: 7676446 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5500. Min Range: -6.5500
Max Act: 6.1125. Min Act: -0.1700
Data Index: 708731 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5500. Min Range: -6.5500
Max Act: 6.1125. Min Act: -0.1700
Data Index: 4073700 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5500. Min Range: -6.5500
Max Act: 6.0500. Min Act: -0.1700
Data Index: 8099890 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5500. Min Range: -6.5500
Max Act: 5.9563. Min Act: -0.1700
Data Index: 3015114 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5500. Min Range: -6.5500
Max Act: 5.9563. Min Act: -0.1700
Data Index: 4215553 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5500. Min Range: -6.5500
Max Act: 5.9250. Min Act: -0.1700
Data Index: 238148 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5500. Min Range: -6.5500
Max Act: 5.8938. Min Act: -0.1700
Data Index: 6436457 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5500. Min Range: -6.5500
Max Act: 5.8625. Min Act: -0.1700
Data Index: 4133815 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5500. Min Range: -6.5500
Max Act: 5.8625. Min Act: -0.1700
Data Index: 8378480 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5500. Min Range: -6.5500
Max Act: 5.8000. Min Act: -0.1700
Data Index: 8155387 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5500. Min Range: -6.5500
Max Act: 5.8000. Min Act: -0.1700
Data Index: 8392826 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5500. Min Range: -6.5500
Max Act: 5.8000. Min Act: -0.1700
Data Index: 5152511 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5500. Min Range: -6.5500
Max Act: 5.8000. Min Act: -0.1700
Data Index: 4094838 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5500. Min Range: -6.5500
Max Act: 5.7688. Min Act: -0.1700
Data Index: 6206597 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5500. Min Range: -6.5500
Max Act: 5.7688. Min Act: -0.1700
Data Index: 2053437 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5500. Min Range: -6.5500
Max Act: 5.7688. Min Act: -0.1700
Data Index: 4518644 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5500. Min Range: -6.5500
Max Act: 5.7688. Min Act: -0.1700
Data Index: 8193157 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5500. Min Range: -6.5500
Max Act: 5.7375. Min Act: -0.1700
Data Index: 4766063 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19