Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3285 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0568. Min Range: -8.0568
Max Act: 8.0568. Min Act: -0.1700
Data Index: 8598028 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0568. Min Range: -8.0568
Max Act: 7.9943. Min Act: -0.1700
Data Index: 996657 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0568. Min Range: -8.0568
Max Act: 7.8693. Min Act: -0.1700
Data Index: 4724242 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0568. Min Range: -8.0568
Max Act: 7.8693. Min Act: -0.1700
Data Index: 4181615 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0568. Min Range: -8.0568
Max Act: 7.9318. Min Act: -0.1700
Data Index: 6262686 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0568. Min Range: -8.0568
Max Act: 7.8693. Min Act: -0.1700
Data Index: 1962417 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0568. Min Range: -8.0568
Max Act: 7.8693. Min Act: -0.1700
Data Index: 996659 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0568. Min Range: -8.0568
Max Act: 7.7443. Min Act: -0.1700
Data Index: 3615101 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0568. Min Range: -8.0568
Max Act: 7.7443. Min Act: -0.1700
Data Index: 6656692 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0568. Min Range: -8.0568
Max Act: 7.6193. Min Act: -0.1700
Data Index: 7538023 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0568. Min Range: -8.0568
Max Act: 7.6818. Min Act: -0.1700
Data Index: 918320 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0568. Min Range: -8.0568
Max Act: 7.6818. Min Act: -0.1700
Data Index: 498161 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0568. Min Range: -8.0568
Max Act: 7.6818. Min Act: -0.1700
Data Index: 160404 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0568. Min Range: -8.0568
Max Act: 7.6818. Min Act: -0.1700
Data Index: 5926647 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0568. Min Range: -8.0568
Max Act: 7.6193. Min Act: -0.1700
Data Index: 594834 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0568. Min Range: -8.0568
Max Act: 7.6193. Min Act: -0.1700
Data Index: 423316 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0568. Min Range: -8.0568
Max Act: 7.6193. Min Act: -0.1700
Data Index: 545896 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0568. Min Range: -8.0568
Max Act: 7.5568. Min Act: -0.1700
Data Index: 68283 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0568. Min Range: -8.0568
Max Act: 7.5568. Min Act: -0.1700
Data Index: 755317 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0568. Min Range: -8.0568
Max Act: 7.5256. Min Act: -0.1700
Data Index: 4301740 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19