Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3056 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4420. Min Range: -7.4420
Max Act: 7.4420. Min Act: -0.1700
Data Index: 8713467 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4420. Min Range: -7.4420
Max Act: 7.2857. Min Act: -0.1700
Data Index: 3197945 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4420. Min Range: -7.4420
Max Act: 7.2232. Min Act: -0.1700
Data Index: 4571682 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4420. Min Range: -7.4420
Max Act: 7.2545. Min Act: -0.1700
Data Index: 5021802 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4420. Min Range: -7.4420
Max Act: 7.2545. Min Act: -0.1700
Data Index: 6191013 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4420. Min Range: -7.4420
Max Act: 7.2232. Min Act: -0.1700
Data Index: 4571660 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4420. Min Range: -7.4420
Max Act: 7.1920. Min Act: -0.1700
Data Index: 5246035 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4420. Min Range: -7.4420
Max Act: 7.2232. Min Act: -0.1700
Data Index: 1307416 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4420. Min Range: -7.4420
Max Act: 7.1920. Min Act: -0.1700
Data Index: 4494000 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4420. Min Range: -7.4420
Max Act: 7.1607. Min Act: -0.1700
Data Index: 5021798 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4420. Min Range: -7.4420
Max Act: 7.2232. Min Act: -0.1700
Data Index: 1604457 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4420. Min Range: -7.4420
Max Act: 7.1607. Min Act: -0.1700
Data Index: 959861 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4420. Min Range: -7.4420
Max Act: 7.1295. Min Act: -0.1700
Data Index: 533143 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4420. Min Range: -7.4420
Max Act: 7.1295. Min Act: -0.1700
Data Index: 5962894 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4420. Min Range: -7.4420
Max Act: 7.1295. Min Act: -0.1700
Data Index: 1645019 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4420. Min Range: -7.4420
Max Act: 7.1295. Min Act: -0.1700
Data Index: 3292971 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4420. Min Range: -7.4420
Max Act: 7.0982. Min Act: -0.1700
Data Index: 573999 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4420. Min Range: -7.4420
Max Act: 7.0982. Min Act: -0.1700
Data Index: 43508 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4420. Min Range: -7.4420
Max Act: 7.1295. Min Act: -0.1700
Data Index: 8000866 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4420. Min Range: -7.4420
Max Act: 7.0357. Min Act: -0.1700
Data Index: 3060399 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19