Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6290 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.9943. Min Act: -0.1700
Data Index: 5821180 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.8693. Min Act: -0.1700
Data Index: 4810457 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.7443. Min Act: -0.1700
Data Index: 7209959 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.6506. Min Act: -0.1700
Data Index: 1549478 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.5568. Min Act: -0.1700
Data Index: 2972038 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.5881. Min Act: -0.1700
Data Index: 2483180 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.5256. Min Act: -0.1700
Data Index: 1122831 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.5256. Min Act: -0.1700
Data Index: 7524458 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.5256. Min Act: -0.1700
Data Index: 7070111 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.4943. Min Act: -0.1700
Data Index: 5658890 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.4943. Min Act: -0.1700
Data Index: 7720746 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.4943. Min Act: -0.1700
Data Index: 8795173 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.4631. Min Act: -0.1700
Data Index: 3548672 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.4631. Min Act: -0.1700
Data Index: 6100019 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.4006. Min Act: -0.1700
Data Index: 6400528 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.4006. Min Act: -0.1700
Data Index: 726127 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.3693. Min Act: -0.1700
Data Index: 7473398 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.3693. Min Act: -0.1700
Data Index: 3264937 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.3381. Min Act: -0.1700
Data Index: 2692884 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.3068. Min Act: -0.1700
Data Index: 3820684 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19