Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5406 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.5040. Min Act: -0.0000

Data Index: 755394 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.3908. Min Act: -0.0000

Data Index: 651933 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.3539. Min Act: -0.0000

Data Index: 1008766 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.3524. Min Act: -0.0000

Data Index: 211556 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.3553. Min Act: -0.0000

Data Index: 1173229 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.3128. Min Act: -0.0000

Data Index: 1238054 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.3230. Min Act: -0.0000

Data Index: 20666 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.3238. Min Act: -0.0000

Data Index: 118 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.3015. Min Act: -0.0000

Data Index: 343931 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.2908. Min Act: -0.0000

Data Index: 862239 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.2991. Min Act: -0.0000

Data Index: 55902 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.3103. Min Act: -0.0000

Data Index: 854164 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.3069. Min Act: -0.0000

Data Index: 851627 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.2956. Min Act: -0.0000

Data Index: 314433 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.2949. Min Act: -0.0000

Data Index: 196652 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.3050. Min Act: -0.0000

Data Index: 923389 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.2687. Min Act: -0.0000

Data Index: 542952 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.2958. Min Act: -0.0000

Data Index: 1265340 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.3022. Min Act: -0.0000

Data Index: 366804 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.2776. Min Act: -0.0000

Data Index: 1109371 (C4 (Web Text))

Max Activating Token Index: 575