Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2908 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0305. Min Range: -4.0305
Max Act: 4.0305. Min Act: -0.1700
Data Index: 6246765 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0305. Min Range: -4.0305
Max Act: 3.8429. Min Act: -0.1700
Data Index: 4620493 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0305. Min Range: -4.0305
Max Act: 3.7803. Min Act: -0.1700
Data Index: 3248446 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0305. Min Range: -4.0305
Max Act: 3.7491. Min Act: -0.1700
Data Index: 1890815 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0305. Min Range: -4.0305
Max Act: 3.7178. Min Act: -0.1700
Data Index: 2024791 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0305. Min Range: -4.0305
Max Act: 3.7021. Min Act: -0.1700
Data Index: 5473274 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0305. Min Range: -4.0305
Max Act: 3.6865. Min Act: -0.1700
Data Index: 2886227 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0305. Min Range: -4.0305
Max Act: 3.6865. Min Act: -0.1700
Data Index: 7257127 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0305. Min Range: -4.0305
Max Act: 3.6396. Min Act: -0.1700
Data Index: 3752891 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0305. Min Range: -4.0305
Max Act: 3.6239. Min Act: -0.1700
Data Index: 1754022 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0305. Min Range: -4.0305
Max Act: 3.6239. Min Act: -0.1700
Data Index: 7423665 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0305. Min Range: -4.0305
Max Act: 3.6083. Min Act: -0.1700
Data Index: 7027038 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0305. Min Range: -4.0305
Max Act: 3.6083. Min Act: -0.1700
Data Index: 2707475 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0305. Min Range: -4.0305
Max Act: 3.5613. Min Act: -0.1700
Data Index: 5186404 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0305. Min Range: -4.0305
Max Act: 3.5456. Min Act: -0.1700
Data Index: 8181712 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0305. Min Range: -4.0305
Max Act: 3.5300. Min Act: -0.1700
Data Index: 1717974 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0305. Min Range: -4.0305
Max Act: 3.5456. Min Act: -0.1700
Data Index: 3592584 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0305. Min Range: -4.0305
Max Act: 3.5456. Min Act: -0.1700
Data Index: 4347564 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0305. Min Range: -4.0305
Max Act: 3.5300. Min Act: -0.1700
Data Index: 543191 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0305. Min Range: -4.0305
Max Act: 3.5456. Min Act: -0.1700
Data Index: 6352365 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19